Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of gsplat

gsplat - v1.5.3

Highlights

gsplat.rasterization now supports render a batch of scenes in one pass. [In addition to its original support of rendering a batch of cameras per scene]

What's Changed

  • Link Jonathan's Tutorial by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/688
  • Fix format README.md by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/689
  • Update README.md by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/690
  • Batchify all APIs by @JunchenLiu77 in https://github.com/nerfstudio-project/gsplat/pull/670
  • fix bug in gsplat-batch.mp4 by @JunchenLiu77 in https://github.com/nerfstudio-project/gsplat/pull/695
  • Update LICENSE by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/699
  • Update Cameras.cuh by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/700
  • Update IntersectTile.cu by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/701
  • Alpha shouldn't be normalized or inversed? by @RongLiu-Leo in https://github.com/nerfstudio-project/gsplat/pull/704
  • Enforce eval3d with UT is set by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/712
  • Update 3dgut.md by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/713
  • New experimental feature: fused bilagrid by @ichsan2895 in https://github.com/nerfstudio-project/gsplat/pull/706
  • Support 2dgs with the latest viewer by @RongLiu-Leo in https://github.com/nerfstudio-project/gsplat/pull/707
  • fix: solves issue, that opacity is reset at iteration 0 by @kleinicke in https://github.com/nerfstudio-project/gsplat/pull/735
  • Add option to disable world space normalization for 2DGS by @JojiJoseph in https://github.com/nerfstudio-project/gsplat/pull/719
  • Fix Fisheye Undistortion. by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/736
  • fix 3dgut sample viewer by @inuex35 in https://github.com/nerfstudio-project/gsplat/pull/734
  • Remove unnecessary abs() calls in scale/opacity loss calculation by @vincentwoo in https://github.com/nerfstudio-project/gsplat/pull/743
  • Fix lack of submodules in CI/CD by @randomze in https://github.com/nerfstudio-project/gsplat/pull/751
  • F-Theta Camera Model Support by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/745
  • Bump to 1.5.3 by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/752
  • update windows server in CI by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/753
  • Use windows 2022 in CI by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/754
  • Add "-allow-unsupported-compiler" for win by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/755
  • Exclude cu118 and cu121 for windows build by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/756

New Contributors

  • @ichsan2895 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/706
  • @kleinicke made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/735
  • @inuex35 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/734
  • @randomze made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/751

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v1.5.2...v1.5.3

- Cuda
Published by liruilong940607 11 months ago

gsplat - v.1.5.3

Highlight

gsplat.rasterization now supports render a batch of scenes in one pass. [In addition to its original support of rendering a batch of cameras per scene]

What's Changed

  • Link Jonathan's Tutorial by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/688
  • Fix format README.md by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/689
  • Update README.md by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/690
  • Batchify all APIs by @JunchenLiu77 in https://github.com/nerfstudio-project/gsplat/pull/670
  • fix bug in gsplat-batch.mp4 by @JunchenLiu77 in https://github.com/nerfstudio-project/gsplat/pull/695
  • Update LICENSE by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/699
  • Update Cameras.cuh by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/700
  • Update IntersectTile.cu by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/701
  • Alpha shouldn't be normalized or inversed? by @RongLiu-Leo in https://github.com/nerfstudio-project/gsplat/pull/704
  • Enforce eval3d with UT is set by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/712
  • Update 3dgut.md by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/713
  • New experimental feature: fused bilagrid by @ichsan2895 in https://github.com/nerfstudio-project/gsplat/pull/706
  • Support 2dgs with the latest viewer by @RongLiu-Leo in https://github.com/nerfstudio-project/gsplat/pull/707
  • fix: solves issue, that opacity is reset at iteration 0 by @kleinicke in https://github.com/nerfstudio-project/gsplat/pull/735
  • Add option to disable world space normalization for 2DGS by @JojiJoseph in https://github.com/nerfstudio-project/gsplat/pull/719
  • Fix Fisheye Undistortion. by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/736
  • fix 3dgut sample viewer by @inuex35 in https://github.com/nerfstudio-project/gsplat/pull/734
  • Remove unnecessary abs() calls in scale/opacity loss calculation by @vincentwoo in https://github.com/nerfstudio-project/gsplat/pull/743
  • Fix lack of submodules in CI/CD by @randomze in https://github.com/nerfstudio-project/gsplat/pull/751
  • F-Theta Camera Model Support by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/745
  • Bump to 1.5.3 by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/752
  • update windows server in CI by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/753

New Contributors

  • @ichsan2895 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/706
  • @kleinicke made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/735
  • @inuex35 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/734
  • @randomze made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/751

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v1.5.2...v.1.5.3

- Cuda
Published by liruilong940607 11 months ago

gsplat - v1.5.2

Highlights

  • 3DGUT is integrated. Now distorted cameras are supported, along with rolling shutter.
  • 2DGS now supports camera gradients (camera pose).
  • full nerfstudio-style viewer supported in the repo.
  • PyPI package fix.

What's Changed

  • Fixed redundant PyTest mark that was applied to a fixture. by @findeevy in https://github.com/nerfstudio-project/gsplat/pull/642
  • Retire 20.04 in workflow by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/643
  • fix workflow PyPI upload by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/644
  • add 2dgs viewmats gradient by @FantasticOven2 in https://github.com/nerfstudio-project/gsplat/pull/645
  • Update rendering.py by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/646
  • Fix spelling: 'principle' => 'principal' by @brentyi in https://github.com/nerfstudio-project/gsplat/pull/647
  • Fix up side down flipping for most of the cases by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/648
  • Fix inverted scene when flipped by @samuelm2 in https://github.com/nerfstudio-project/gsplat/pull/656
  • New Viewer with nerfview=0.1.2 by @JunchenLiu77 in https://github.com/nerfstudio-project/gsplat/pull/657
  • Simplify tight rectangular bounding box calculation by @zerolover in https://github.com/nerfstudio-project/gsplat/pull/662
  • [BUG] Fix strict "invalid mask" in gsplat.utils.save_ply(...) by @Crezle in https://github.com/nerfstudio-project/gsplat/pull/663
  • Multiple minor fixes and update citation by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/664
  • Increase maximum allowed far plane in viewer by @vincentwoo in https://github.com/nerfstudio-project/gsplat/pull/672
  • Implement 3DGUT by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/667
  • Update nerfview dep by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/673
  • use c++17 by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/675
  • expose learning rates in simple_trainer.py by @MrNeRF in https://github.com/nerfstudio-project/gsplat/pull/676
  • Minor fix by @RongLiu-Leo in https://github.com/nerfstudio-project/gsplat/pull/677
  • fix instructions by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/679
  • fix format by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/680
  • Fix jitcompile arguments for torch>=2.7.0 by @shiukaheng in https://github.com/nerfstudio-project/gsplat/pull/651
  • Fix manifest and upgrade to 1.5.2 by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/685

New Contributors

  • @findeevy made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/642
  • @samuelm2 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/656
  • @zerolover made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/662
  • @Crezle made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/663
  • @vincentwoo made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/672
  • @RongLiu-Leo made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/677

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v1.5.1...v1.5.2

- Cuda
Published by liruilong940607 about 1 year ago

gsplat - v1.5.1

Highlights

New exporter python api: from gsplat import export_splats, supprts three exporting formats (#628, #640): * .ply: A standard PLY file format. Supported by most viewers. * .splat: A custom Splat file format. Supported by antimatter15 viewer. * .ply_compressed: A compressed PLY file format. Used by Supersplat viewer.

What's Changed

  • Update publish.yml by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/621
  • faster fused-ssim by @MrNeRF in https://github.com/nerfstudio-project/gsplat/pull/622
  • Added Gaussian Splat Exporters by @bolopenguin in https://github.com/nerfstudio-project/gsplat/pull/628
  • Fix typo in strategy.rst code example by @buesma in https://github.com/nerfstudio-project/gsplat/pull/632
  • Multiple small fixes by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/638
  • slightly adjusting atol for test by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/639
  • :bug: Fix memory leak in exporters - splat2ply bytes by @mrcabellom in https://github.com/nerfstudio-project/gsplat/pull/640
  • bump to 1.5.1 by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/641

New Contributors

  • @bolopenguin made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/628
  • @buesma made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/632
  • @mrcabellom made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/640

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v1.5.0...v1.5.1

- Cuda
Published by liruilong940607 about 1 year ago

gsplat - v1.5.0

Highlights

  • 3.5x faster compilation (4m19s -> 1m22s) via code refactoring.
  • up to 25% faster rasterization function via more accurate GS-tile intersection.
  • support CUDA fused Adam Optimizer with mask support (from gsplat.optimizers import SelectiveAdam)

What's Changed

  • A set of comments and annotations to 2DGS CUDA kernels by @DylanWaken in https://github.com/nerfstudio-project/gsplat/pull/429
  • densify after optimizer step. fixes #426 by @rahul-goel in https://github.com/nerfstudio-project/gsplat/pull/431
  • Fix 2DGS for Correct Normal and Median Depth Calculation by @khokao in https://github.com/nerfstudio-project/gsplat/pull/430
  • Selective Adam by @rahul-goel in https://github.com/nerfstudio-project/gsplat/pull/432
  • Fix PyPI upload missing whl file by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/454
  • add-support-for-non-trainable-params by @nikmo33 in https://github.com/nerfstudio-project/gsplat/pull/456
  • remove unused code by @georghess in https://github.com/nerfstudio-project/gsplat/pull/482
  • Reorganize file structure by @JunchenLiu77 in https://github.com/nerfstudio-project/gsplat/pull/480
  • Fix inconsistency in the comments by @JiangWenPL in https://github.com/nerfstudio-project/gsplat/pull/441
  • bugfix in rasterization2d_inria by @Golbstein in https://github.com/nerfstudio-project/gsplat/pull/499
  • use mask in 2dgs by @Golbstein in https://github.com/nerfstudio-project/gsplat/pull/497
  • Fix proj.cuh include guard by @desmondlzy in https://github.com/nerfstudio-project/gsplat/pull/504
  • Fix evaluation scripts by @rjbaw in https://github.com/nerfstudio-project/gsplat/pull/510
  • Reduce ram usage using fisheye as camera model by @aW4KeNiNG in https://github.com/nerfstudio-project/gsplat/pull/521
  • Implement gaussian splatting ply file saving with o3d by @MrNeRF in https://github.com/nerfstudio-project/gsplat/pull/427
  • Avoid jpeg compression artifacts when training Mip-NeRF360. by @jefequien in https://github.com/nerfstudio-project/gsplat/pull/507
  • Update nerfview version in examples to avoid division by zero by @MotivaCG in https://github.com/nerfstudio-project/gsplat/pull/558
  • minor fix to 2dgs corner case by @FantasticOven2 in https://github.com/nerfstudio-project/gsplat/pull/543
  • refactor CUDA code for faster compilation and easier extensibility by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/583
  • Fix minor typo in documentation about rasterization by @kikirizki in https://github.com/nerfstudio-project/gsplat/pull/580
  • Fix incorrect comments for view matrices by @ScaryPG in https://github.com/nerfstudio-project/gsplat/pull/579
  • fix the offset of K in projection packed fwd 2dgs kernel by @lapisliu in https://github.com/nerfstudio-project/gsplat/pull/569
  • Fix channel padding for distortion and median depth computation by @jonathsch in https://github.com/nerfstudio-project/gsplat/pull/559
  • Add disablevideo flag for simpletrainer by @MotivaCG in https://github.com/nerfstudio-project/gsplat/pull/557
  • fix: wrong torch cat dim when concatenating colors+depths in simpletrainer2dgs.py by @Crescent-Saturn in https://github.com/nerfstudio-project/gsplat/pull/508
  • Fixes build issues by @MrNeRF in https://github.com/nerfstudio-project/gsplat/pull/585
  • move env yml to examples/ by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/587
  • remove env yml by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/588
  • Update _backend.py by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/589
  • fix save ply if else by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/594
  • Rect cull by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/596
  • Optionally leverage opacity to tight the radii bounding box by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/597
  • fix ALPHA_THRESHOLD by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/598
  • fix setup.py for build by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/602
  • Disable Auto Precompiled Header. Support Enabling it Manually. by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/603
  • fix tight opa by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/606
  • Fix build action: Upgraded upload-artifact@v3 / download-artifact@v3 -> upload-artifact@v4 / download-artifact@v4 by @shiukaheng in https://github.com/nerfstudio-project/gsplat/pull/616
  • fix adam shape issue by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/618
  • delay import for checkandbuildextensionhprecompiler_headers by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/619
  • bump to 1.5.0 by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/620

New Contributors

  • @DylanWaken made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/429
  • @khokao made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/430
  • @nikmo33 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/456
  • @georghess made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/482
  • @JunchenLiu77 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/480
  • @JiangWenPL made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/441
  • @Golbstein made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/499
  • @desmondlzy made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/504
  • @rjbaw made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/510
  • @aW4KeNiNG made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/521
  • @MotivaCG made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/558
  • @kikirizki made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/580
  • @ScaryPG made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/579
  • @lapisliu made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/569
  • @jonathsch made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/559
  • @Crescent-Saturn made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/508
  • @shiukaheng made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/616

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v1.4.0...v1.5.0

- Cuda
Published by liruilong940607 about 1 year ago

gsplat - v1.4.0

Highlights

  • support 2DGS
  • Camera model: perspective, orthogonal, fish-eye
  • Start to support pre-built wheels (python 10)

What's Changed

  • Update build workflow by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/369
  • fix (apparant) typos in compression docs by @christian-helms in https://github.com/nerfstudio-project/gsplat/pull/370
  • eval supports multi-GPU by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/371
  • correct a typo to fix #373 by @jckhng in https://github.com/nerfstudio-project/gsplat/pull/383
  • Add option to render camera trajectory as an ellipse. by @jefequien in https://github.com/nerfstudio-project/gsplat/pull/380
  • Add an option to disable world space normalization in examples/simple_trainer.py by @JojiJoseph in https://github.com/nerfstudio-project/gsplat/pull/379
  • Fix points projection when sampling patches for training by @nnop in https://github.com/nerfstudio-project/gsplat/pull/386
  • fix reshape error when multi GPU bachsize > 1 not packed by @Ultized in https://github.com/nerfstudio-project/gsplat/pull/382
  • Fix typo by @cr333 in https://github.com/nerfstudio-project/gsplat/pull/392
  • Make download script work on Windows, too by @cr333 in https://github.com/nerfstudio-project/gsplat/pull/397
  • Fused differentiable SSIM by @rahul-goel in https://github.com/nerfstudio-project/gsplat/pull/396
  • 2DGS by @FantasticOven2 in https://github.com/nerfstudio-project/gsplat/pull/208
  • citation.bib by @maturk in https://github.com/nerfstudio-project/gsplat/pull/400
  • Implement Bilateral Guided Gaussian Splatting. by @jefequien in https://github.com/nerfstudio-project/gsplat/pull/291
  • Bump fused-ssim commit by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/405
  • Update rendering.py by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/407
  • Update CITATION.bib by @cr333 in https://github.com/nerfstudio-project/gsplat/pull/410
  • Make commands easier in README by @MrNeRF in https://github.com/nerfstudio-project/gsplat/pull/420
  • Implement Fisheye-GS. by @jefequien in https://github.com/nerfstudio-project/gsplat/pull/398
  • Publish precompiled wheels in Github release and add wheel index by @martinResearch in https://github.com/nerfstudio-project/gsplat/pull/365
  • 1.4.0 by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/421
  • fix workflow by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/422
  • Workflow fix by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/423

New Contributors

  • @christian-helms made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/370
  • @jckhng made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/383
  • @JojiJoseph made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/379
  • @nnop made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/386
  • @Ultized made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/382
  • @cr333 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/392
  • @rahul-goel made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/396
  • @FantasticOven2 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/208
  • @MrNeRF made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/420
  • @martinResearch made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/365

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v1.3.0...v1.4.0

- Cuda
Published by liruilong940607 over 1 year ago

gsplat - v1.3.0

Highlight

  • Support 3DGS Compression
  • Support orthographic projection
  • Support TanksAndTemples Dataset
  • Various Bug Fix

What's Changed

  • Make sure the build directory exists. by @keunhong in https://github.com/nerfstudio-project/gsplat/pull/319
  • docs: update README.md by @eltociear in https://github.com/nerfstudio-project/gsplat/pull/322
  • Fix typo in examples/simple_viewer.py by @simo23 in https://github.com/nerfstudio-project/gsplat/pull/321
  • Consolidate simpletrainer.py and simpletrainer_mcmc.py by @brentyi in https://github.com/nerfstudio-project/gsplat/pull/325
  • Compressing gaussian splats by @jefequien in https://github.com/nerfstudio-project/gsplat/pull/309
  • Simplify tyro usage in simple_trainer.py by @brentyi in https://github.com/nerfstudio-project/gsplat/pull/332
  • Cleanup C/CUDA code for C users by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/333
  • Patch to make Strategy compatible with splatfacto by @kerrj in https://github.com/nerfstudio-project/gsplat/pull/334
  • Fix minor typo by @zhiguotang5 in https://github.com/nerfstudio-project/gsplat/pull/342
  • correct distCoeffs of SIMPLE_RADIAL by @Master-cai in https://github.com/nerfstudio-project/gsplat/pull/337
  • Add np.random.choice fallback for many Gaussians exceeding torch.multinomial limits by @soskek in https://github.com/nerfstudio-project/gsplat/pull/338
  • data parser for t&t dataset by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/347
  • Added orthographic projection by @VladislavZavadskyy in https://github.com/nerfstudio-project/gsplat/pull/349
  • Fix bug related to refinescale2d and add pauserefineafterreset to default strategy by @jb-ye in https://github.com/nerfstudio-project/gsplat/pull/354
  • tt compression script by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/357
  • Update to 1.3.0 by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/366

New Contributors

  • @keunhong made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/319
  • @simo23 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/321
  • @zhiguotang5 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/342
  • @Master-cai made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/337
  • @soskek made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/338
  • @VladislavZavadskyy made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/349

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v1.2.0...v1.3.0

- Cuda
Published by liruilong940607 almost 2 years ago

gsplat - v1.2.0

Highlight

Multi-GPU distributed rasterization is supported! E.g. 4 GPUs could lead to more than 3x speedup as well as 3x less memory usage at the same time.

What's Changed

  • [Docs] Evaluation metrics for mcmc, antialiased, and absgrad. by @maturk in https://github.com/nerfstudio-project/gsplat/pull/300
  • Update requirements.txt by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/308
  • Fix projection for images with non-centered camera (e.g. crops) by @JonathonLuiten in https://github.com/nerfstudio-project/gsplat/pull/305
  • prevent race condition when JIT in multiprocess by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/312
  • Support Multi-GPU training based on the paper "On Scaling Up 3D Gaussian Splatting Training" by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/253
  • Update version.py by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/313

New Contributors

  • @JonathonLuiten made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/305

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v1.1.1...v1.2.0

- Cuda
Published by liruilong940607 almost 2 years ago

gsplat - v0.1.13

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v0.1.12...v0.1.13

- Cuda
Published by jb-ye almost 2 years ago

gsplat - v1.1.1

What's Changed

hot fix

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v1.1.0...v1.1.1

- Cuda
Published by liruilong940607 almost 2 years ago

gsplat - v1.1.0

Highlight

Multiple densification strategies are now supported in gsplat, including - DefaultStrategy(): The original 3DGS densification process. - DefaultStrategy(absgrad=True): Densification process from "AbsGS: Recovering Fine Details for 3D Gaussian Splatting" - MCMCStrategy(). Densification process from "3D Gaussian Splatting as Markov Chain Monte Carlo"

What's Changed

  • Update 3DGS examples to use the latest nerfview from pypi by @hangg7 in https://github.com/nerfstudio-project/gsplat/pull/206
  • docs: update README.md by @eltociear in https://github.com/nerfstudio-project/gsplat/pull/210
  • Added a guidance for installing gsplat on Windows by @KevinXu02 in https://github.com/nerfstudio-project/gsplat/pull/213
  • Minor fix for _QuatScaleToCovarPreci back with sparse grad by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/214
  • Fix wrong description in rasterization API doc by @yifanlu0227 in https://github.com/nerfstudio-project/gsplat/pull/216
  • support 2^n+1 channels for rasterizetopixels by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/218
  • workaround for n-dim rendering with n>32 by @wuzirui in https://github.com/nerfstudio-project/gsplat/pull/217
  • Minor fix for _RasterizeToPixels back to avoid NaNs by @opipari in https://github.com/nerfstudio-project/gsplat/pull/235
  • clean up the shape of the colors by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/228
  • static shared mem -> dynamic shared mem by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/229
  • updating background for different rendering modes [D, ED, RGB+D, RGB+… by @vye16 in https://github.com/nerfstudio-project/gsplat/pull/240
  • Fix max_range in _torch_impl._rasterize_to_pixels() by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/242
  • Implement 3DGS-MCMC in gsplat. by @jefequien in https://github.com/nerfstudio-project/gsplat/pull/238
  • sqrt int to float by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/246
  • Clamp ratios in MCMC's compute_relocation by @yzslab in https://github.com/nerfstudio-project/gsplat/pull/247
  • add poetry files, and fix numpy error and no data error. by @MasahiroOgawa in https://github.com/nerfstudio-project/gsplat/pull/251
  • Separate C source into many translation units by @fwilliams in https://github.com/nerfstudio-project/gsplat/pull/255
  • Fwilliams/fix headers and ninja by @fwilliams in https://github.com/nerfstudio-project/gsplat/pull/256
  • template everything but don't actually support multiple precisions yet by @fwilliams in https://github.com/nerfstudio-project/gsplat/pull/259
  • fix glm path in JIT building by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/260
  • Fwilliams/atomics by @fwilliams in https://github.com/nerfstudio-project/gsplat/pull/261
  • set the MAX_JOBS to 10 if not set. by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/262
  • float3 -> vec3; float2 -> vec2; by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/267
  • Start adding support for double, float16, and bfloat16 by @fwilliams in https://github.com/nerfstudio-project/gsplat/pull/270
  • fix testfullyfusedprojectionpacked test by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/289
  • Add optional masks in rasterize_to_pixels() to support Grendel by @alexis-mmm in https://github.com/nerfstudio-project/gsplat/pull/284
  • Abstracting out the GS heuristics into a Strategy class by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/278
  • Bump to 1.1.0 by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/290

New Contributors

  • @yifanlu0227 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/216
  • @wuzirui made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/217
  • @opipari made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/235
  • @jefequien made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/238
  • @yzslab made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/247
  • @MasahiroOgawa made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/251
  • @fwilliams made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/255
  • @alexis-mmm made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/284

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v1.0.0...v1.1.0

- Cuda
Published by liruilong940607 almost 2 years ago

gsplat - v1.0.0

A Major Update to V1.0.0

  • Comparing to the official implementation, gsplat enables up to 4x less training memory footprint, and up to 2x less training time on Mip-NeRF 360 captures, and potential more on larger scenes.

  • Support extremely large scene rendering, which is magnitudes faster than the official CUDA backend diff-gaussian-rasterization.

  • Extra features, including batch rasterization, N-D feature rendering (faster), depth rendering, sparse gradient etc.

- Cuda
Published by liruilong940607 almost 2 years ago

gsplat - v.0.1.12

What's Changed

  • Add backward gradient for background by @KevinXu02 in https://github.com/nerfstudio-project/gsplat/pull/170
  • enable doc versioning by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/185
  • Fix version value for Sphinx by @brentyi in https://github.com/nerfstudio-project/gsplat/pull/191
  • Improve numerical stability of torchimpl.projectcov3dewa by @oseiskar in https://github.com/nerfstudio-project/gsplat/pull/182
  • Update project_pix to use eps by @SimonF24 in https://github.com/nerfstudio-project/gsplat/pull/192
  • create JIT compilation configs if necessary by @ychfan in https://github.com/nerfstudio-project/gsplat/pull/164

New Contributors

  • @KevinXu02 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/170
  • @SimonF24 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/192
  • @ychfan made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/164

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v0.1.11...v.0.1.12

- Cuda
Published by liruilong940607 about 2 years ago

gsplat - v0.1.11

What's Changed

  • Fast SH implementation by @jb-ye in https://github.com/nerfstudio-project/gsplat/pull/165
  • return result array for lower sh degrees by @YertleTurtleGit in https://github.com/nerfstudio-project/gsplat/pull/171
  • Implement AbsGS by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/166

New Contributors

  • @YertleTurtleGit made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/171

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v0.1.10...v0.1.11

- Cuda
Published by kerrj about 2 years ago

gsplat - v0.1.10

What's Changed

  • Fix missing +0.5 in calculating uv coordinate by @jb-ye in https://github.com/nerfstudio-project/gsplat/pull/151
  • Check for normalized quats. by @Mxbonn in https://github.com/nerfstudio-project/gsplat/pull/155

New Contributors

  • @Mxbonn made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/155

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v0.1.9...v0.1.10

- Cuda
Published by jb-ye about 2 years ago

gsplat - v0.1.9

What's Changed

  • Small CUDA changes for nd rasterization by @kerrj in https://github.com/nerfstudio-project/gsplat/pull/144
  • Remove redundant projection matrix by @oseiskar in https://github.com/nerfstudio-project/gsplat/pull/97
  • Approximate view matrix gradient for pose optimization by @oseiskar in https://github.com/nerfstudio-project/gsplat/pull/127

New Contributors

  • @oseiskar made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/97

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v0.1.8...v0.1.9

- Cuda
Published by kerrj about 2 years ago

gsplat - v0.1.8

What's Changed

Some quality improvements because of:

  • Fix vmean3d in projectg and vconic calculation in *rasterizebackward by @jb-ye in https://github.com/nerfstudio-project/gsplat/pull/139
  • add backprop grad of opacity compensation by @jb-ye in https://github.com/nerfstudio-project/gsplat/pull/140

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v0.1.7...v0.1.8

- Cuda
Published by kerrj about 2 years ago

gsplat - v0.1.7

What's Changed

  • Eval table by @AdamRashid96 in https://github.com/nerfstudio-project/gsplat/pull/134
  • add device guard by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/135
  • Fix backprop grad of cov2d / scales and unit tests by @jb-ye in https://github.com/nerfstudio-project/gsplat/pull/136

New Contributors

  • @AdamRashid96 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/134

Full Changelog: https://github.com/nerfstudio-project/gsplat/compare/v0.1.6...v0.1.7

- Cuda
Published by kerrj over 2 years ago

gsplat - v0.1.6

What's new

The python interface for tile_bounds has been abstracted away, and instead project and rasterize take in a block_width parameter controlling the tile size as well as the CUDA block size. CUDA was refactored to allow dynamic block sizes, which enables ND rasterization speedups by taking better advantage of shared memory.

- Cuda
Published by kerrj over 2 years ago

gsplat - v0.1.5

What's new?

  • Improved pytorch implementation of project_gaussians inside torchimpl.py
  • Screen space blur compensation for rasterizing tiny gaussians from Mip-Splatting
  • Bugfixes

- Cuda
Published by kerrj over 2 years ago

gsplat - v0.1.4

What's Changed

Fix a major bug in rasterization since version 0.1.0. (Issue and PR)

- Cuda
Published by liruilong940607 over 2 years ago

gsplat - v0.1.3

What's changed

  • Alpha rendering and supervision with return_alpha flag in rasterize.py
  • Fix bug with 0 gaussians in view

- Cuda
Published by kerrj over 2 years ago

gsplat - v0.1.2

What's Changed

  • Fixing latent issue with single intersection
  • API update: Function.apply() will be deprecated soon. It's recommend to directly call the python functions. The full list of updates:
    • ProjectGaussians.apply -> project_gaussians
    • RasterizeGaussians.apply / NDRasterizeGaussians.apply -> rasterize_gaussians
    • BinAndSortGaussians.apply -> bin_and_sort_gaussians
    • ComputeCumulativeIntersects.apply -> compute_cumulative_intersects
    • ComputeCov2dBounds.apply -> compute_cov2d_bounds
    • GetTileBinEdges.apply -> get_tile_bin_edges
    • MapGaussiansToIntersects.apply -> map_gaussian_to_intersects
    • SphericalHarmonics.apply -> spherical_harmonics

- Cuda
Published by liruilong940607 over 2 years ago

gsplat - v0.1.1

A few small fixes:

  • Build might stuck if Ninja got interrupted with a lock file uncleaned.
  • Assert in ND Rasterization.

- Cuda
Published by liruilong940607 over 2 years ago

gsplat - v0.1.0

Highlights

Support ND features for Gaussians.

- Cuda
Published by liruilong940607 over 2 years ago