v1.0.0

Highlights

• New splatfacto model, built on the gsplat implementation of INRIA's 2023 Gaussian Splatting algorithm.
• Complete rewrite of the viewer, now built entirely on viser.
• Project Aria and EyefulTower dataset support, and COLMAP pipeline improvements.

...and much more, thanks to the 60+ contributors who helped make this happen! See below.

What's Changed

• Add background_color config to keep consistent with other models by @kobejean in #2455
• Do not materialize mlp_head if no field_heads by @Mxbonn in #2457
• .vscode settings match move to ms-python.black-formatter by @Mxbonn in #2456
• Migrate doc from RTD to gh-pages by @liruilong940607 in #2460
• Allow custom sampler in ProposalNetworkSampler by @Mxbonn in #2464
• Fix COLMAP dataparser masks and depthmaps by @jkulhanek in #2467
• Track all viser GUI folders to avoid folder duplicates (viewer-beta) by @chungmin99 in #2466
• Update colmap installation instructions with conda by @ginazhouhuiwu in #2473
• Update doc.yml by @liruilong940607 in #2479
• Remove rtd by @tancik in #2478
• Don't deploy docs from pull requests by @brentyi in #2482
• fix:correction of PairPixelSampler in case of using masks with depth-nerfacto by @pierremerriaux-leddartech in #2477
• ns-render - render all images by @jkulhanek in #2459
• fixing broken links in README by @ARK3r in #2483
• Fourier Feature encodings and polyhedron encodings by @Mxbonn in #2463
• fixed link to viser to be functional link cause previous 404ed by @THE-COB in #2486
• Add support of using both Comet and Viewer at the same time by @Lothiraldan in #2488
• Fix DatasetRender to override dataset path only when provided by @sjj118 in #2494
• Remove unused config param by @tancik in #2495
• (minor) Align upsampling in TensorCPEncoding with TensorVMEncoding by @Dwawayu in #2493
• Add documentation about unknown depth pixel convention by @jampekka in #2490
• patch for mkdirs on camera path json filepath by @kerrj in #2502
• Move camera optimization out of datamanager and parallelize dataloading by @kerrj in #2092
• minor patch for exporting pcs and meshes with parallel datamanager by @kerrj in #2503
• Fix jitter viewer by @kerrj in #2505
• Add ODM data processor by @pierotofy in #2517
• Upgrade pyright by @brentyi in #2526
• Update URLs for readme and image references by @cvachha in #2527
• Add camera_type dropdown in new viewer by @cvachha in #2525
• Fix datamanagers' get_rays_per_batch functions in case of using DynamicBatchPipeline by @sjj118 in #2522
• Bump tyro to 0.5.10 by @brentyi in #2393
• Update data_conventions.md by @SeaOtocinclus in #2534
• Fix pillow version to avoid error with ANTIALIAS (Fix #2378) by @ahmed-shariff in #2446
• Fix multiclient jitter with separate render threads for each client by @ginazhouhuiwu in #2519
• Add scannetpp dataparser by @liu115 in #2498
• minor typing error by @Shiva-Gantha in #2545
• Missing a space in base_datamanager.py by @OrangeSodahub in #2546
• Fix pixel-perfect-sfm installation in Dockerfile by @2b-t in #2549
• static imgs never rendered in multiclient by @kerrj in #2551
• Move only per-chunk data to the GPU to support rendering large images by @decrispell in #2481
• make refine intrinsics during ns-process-data optional by @machenmusik in #2550
• Few viewer changes by @cvachha in #2553
• ns-process-data images fix: multinerf uses equals sign by @machenmusik in #2558
• Add gradient scaling option to more methods by @kobejean in #2555
• Expose camera frustums size and occlusions to CLI by @ethanweber in #2556
• Make resetting the near_plane in NearFarCollider optional. by @Mxbonn in #2465
• Print beta URL in banner correctly by @kerrj in #2569
• Fix torch.compile for torch 2.1 by @jkulhanek in #2577
• Remove compile line in camera_utils by @ginazhouhuiwu in #2584
• Fix HTML render of README.md by @krahets in #2599
• Render nearest training view by @AdamRashid96 in #2384
• Make spherical harmonics test more forgiving by @brentyi in #2607
• Update LICENSE by @cpheinrich in #2597
• Remove an outdated comment in RayGenerator class by @emmaguo13 in #2606
• Added UI to load camera path from existing path for the dataset by @THE-COB in #2530
• Bugfix; scrape pipeline for viewercontrol, not trainer by @chungmin99 in #2621
• Remove PCA colormap bug for float output maps by @chungmin99 in #2620
• Fix tangential camera distortion (p1,p2 in opencv camera) by @jkulhanek in #2627
• Integrate scene click capability from original viewer by @chungmin99 in #2509
• Keyframe timing for beta viewer by @brentyi in #2638
• Patch spiral rendering w/ parallel datamanager by @kerrj in #2637
• Bugfix: shape confusion in resizing by @Yosshi999 in #2565
• Make nuScenes dataparser compatible with ParallelDataManager by @dmholtz in #2635
• fix include_input for NeRFEncoding by @blacksino in #2642
• Converted many @DataClass assignments for python 3.11 compatibility by @jaggzh in #2630
• Mps fix by @Jerry-Master in #2436
• Fixes bug in PairPixelSampler when working with masked dataset by @padeler in #2368
• Encoder + MLP combo by @ethanweber in #2063
• Ns-process-data bug with dev version of colmap by @AdamRashid96 in #2651
• Fix typos by @omahs in #2655
• Update hloc and add new matcher types by @alexandrukis in #2658
• Trainer can now always save dataparser transform by @pwais in #2653
• Update dependencies for M1 Macs by @brentyi in #2665
• Update cameras.py - removed duplicate lines by @IamMohitM in #2661
• Fix large dataset (> 512 images) training in viewer_beta by @brentyi in #2669
• Add support for Project Aria datasets. by @sweeneychris in #2617
• Fix custom data links in README by @brentyi in #2671
• Parity of layout between viewer beta and legacy viewer by @kerrj in #2639
• Update first_nerf.md by @Lothiraldan in #2677
• [Fix] Pixel Sampler setup in VanillaDataManager for Cameras incl. metadata by @tobiasfshr in #2678
• Added support for .tif and .tiff files in equirect utils by @THE-COB in #2613
• Gaussian splatting by @kerrj in #2521
• Add instructions for data collection and processing with Spectacular AI tools by @oseiskar in #2668
• Fix a bug of random quaternions by @Zhuoyang-Pan in #2687
• fixed color issue in ply file by @hardikdava in #2693
• Improved render panel for beta viewer by @brentyi in #2667
• Fix dycheck depth and rgb rescale by @origamiman72 in #2623
• Adding docs for Instruct-GS2GS by @cvachha in #2702
• Fix periodically stuck in parallel datamanager by @liruilong940607 in #2713
• allow render path to exist by @maturk in #2710
• Add visible as kwarg to ViewerElements by @chungmin99 in #2730
• Add orthophoto rendering support. by @LeaFendd in #2648
• Improvement to Gaussian Splatting workflow by @jb-ye in #2709
• fixed not cache images for full image datamanager by @hardikdava in #2692
• Fixed nerfstudio logo at the top of Colab notebook by @akristoffersen in #2733
• Migrate to viser viewer by @tancik in #2515
• Add PyNeRF external method by @hturki in #2734
• Add Mill 19 dataset by @hturki in #2742
• Undistortion should not occur for already-undistorted images by @liorfritz in #2726
• Fix Python 3.11 dataclass field default_factory defaults by @ringohoffman in #2746
• Viewer depth compositing for Gaussian Splatting models by @brentyi in #2744
• Update docs to recommend torch 2.1 by @brentyi in #2748
• Fix apple silicon install 3.10+ by @ringohoffman in #2752
• Add --no-cache-dir option to pip install in Dockerfile by @bro-sin in #2739
• Improve viewer banner when server is bound to 0.0.0.0 by @brentyi in #2761
• Use ruff as linter and formatter by @ringohoffman in #2765
• Setting save_world_frame as False by default and Splat export panel in viewer by @cvachha in #2700
• Remove deprecated dependency_links config by @ringohoffman in #2753
• Remove unused make_share_url arg in ns-viewer by @brentyi in #2749
• Update dependencies for aarch64 by @ymtoo in #2750
• Reduce startup overhead by @brentyi in #2763
• camtoworld is already a tensor in sdfstudio_data by @maturk in #2777
• Docs for gaussian splatting by @kerrj in #2776
• Bump viser by @brentyi in #2779
• Update documentation for 3DGS by @cvachha in #2780
• Speed up mask sampling with rejection sampling by @anc2001 in #2585
• Migrate to python functions for gsplat by @kerrj in #2778
• Add option of caching image in bytes rather than float32 by @jb-ye in #2741
• Updates to docs for gaussian splatting by @AdamRashid96 in #2782
• MAX_AUTO_RESOLUTION is ensured in auto downscale by @jb-ye in #2788
• Remove unsupported camera optimization from GS by @kerrj in #2790
• Bump tyro by @brentyi in #2792
• Revisiting #1504 and fix colmap world coordinate transform by @jb-ye in #2793
• Switching the gaussian-splatting dataparser from ColmapDataParser to NerfStudioDataparser and updating ns-process-data by @CardiacMangoes in #2791
• Don't throw away non-tensor objects in TensorDataclass by @brentyi in #2783
• Use github output format for ruff in CI by @brentyi in #2786
• Gaussian splatting support for Aria by @brentyi in #2785
• Disable projectaria tools on Windows by @VasuAgrawal in #2794
• Rename gaussian-splatting to splatfacto for clarity by @kerrj in #2796
• Add preliminary EyefulTower dataset support by @VasuAgrawal in #2672
• Gracefuly handle old ViewerElements from legacy viewer by @kerrj in #2797
• Remove legacy viewer from GitHub actions by @brentyi in #2798
• Clean up ns-train {method} --help for not-yet-installed external methods by @brentyi in #2760
• fix the bugs associated with blender datas by @KevinXu02 in #2704

New Contributors

• @pierremerriaux-leddartech made their first contribution in #2477
• @ARK3r made their first contribution in #2483
• @Lothiraldan made their first contribution in #2488
• @sjj118 made their first contribution in #2494
• @Dwawayu made their first contribution in #2493
• @jampekka made their first contribution in #2490
• @pierotofy made their first contribution in #2517
• @SeaOtocinclus made their first contribution in #2534
• @ahmed-shariff made their first contribution in #2446
• @OrangeSodahub made their first contribution in #2546
• @2b-t made their first contribution in #2549
• @cpheinrich made their first contribution in #2597
• @emmaguo13 made their first contribution in #2606
• @Yosshi999 made their first contribution in #2565
• @dmholtz made their first contribution in #2635
• @blacksino made their first contribution in #2642
• @jaggzh made their first contribution in #2630
• @Jerry-Master made their first contribution in #2436
• @omahs made their first contribution in #2655
• @alexandrukis made their first contribution in #2658
• @IamMohitM made their first contribution in #2661
• @sweeneychris made their first contribution in #2617
• @tobiasfshr made their first contribution in #2678
• @oseiskar made their first contribution in #2668
• @hardikdava made their first contribution in #2693
• @LeaFendd made their first contribution in #2648
• @liorfritz made their first contribution in #2726
• @ringohoffman made their first contribution in #2746
• @bro-sin made their first contribution in #2739
• @ymtoo made their first contribution in #2750
• @VasuAgrawal made their first contribution in #2794
• @KevinXu02 made their first contribution in #2704

Full Changelog: v0.3.4...v1.0.0