v1.1.0

What's Changed

• Refactor ScenePointerCallbacks for viser compatibility by @chungmin99 in #3036
• Only load+undistort splatfacto images when they're used by @brentyi in #3043
• New Google Drive link for poster dataset by @ginazhouhuiwu in #3045
• Added SIGNeRF to Nerfstudio methods by @JDihlmann in #3053
• Make colmapDataParser compatible with 360_v2 dataset format by @Jing1Ling in #2860
• Fix config loading for Eyeful Tower dataset by @hardhat5 in #3054
• feat(ci): migrate to uv in CI by @SauravMaheshkar in #3038
• Fix custom elements nested under @Property by @kerrj in #3066
• fix exporter.py for FullImageDataManager and RandomCamerasDataManager by @dberga in #3065
• Camera pose optimization for Splatfacto by @oseiskar in #2891
• write eval combined images for diagnostics by @jb-ye in #3070
• Fixed Unexpectedly huge RAM consumption of parallel datamanager by @hyperzy in #3060
• Add pointcloud loading for blender parser by @gchhablani in #2902
• shift principle points by .5 in undistortion by @kerrj in #3071
• Fix call to detect ODM reconstruction file by @codeprimate in #3018
• updates to apply_pca_colormap by @kerrj in #3086
• Changes for trainer.py to support the Gradio webui by @KevinXu02 in #3046
• Allow alpha transparency training for blender datasets input by @jb-ye in #3088
• Hloc fix for image_ids (camera per image) by @dberga in #3081
• Adding lock for Viser Element callbacks by @Satvik1701 in #3067
• Adding cropping for gaussian splat exports by @THE-COB in #3105
• GaussianSplats export: allow uint8 in ply by @mathijshenquet in #3111
• Use AbsGrad to get better results with less gaussians by @jb-ye in #3113
• Fix bug in pixel sampler by @carlinds in #3103
• metashape_utils: work with camera groups by @f-dy in #2626
• Fix #3064 and some minor changes by @jb-ye in #3121
• Support splatfacto training for metashape exports by @jb-ye in #3122
• fix nerfstudio collate function by @hturki in #2965
• Add a pointcloud export from polycam to process-data by @kerrj in #3124
• BioNeRF by @Leandropassosjr in #3125
• Fixing typos and symbols in bionerf.md by @Leandropassosjr in #3126
• Add kwargs handling for patchpixelsampler patch size by @chungmin99 in #2622
• Make RealityCapture csv/ply exports work! by @jb-ye in #3131
• adding the link for the paper page and fixing image paths by @Leandropassosjr in #3132
• Fix edge case of depth colormap by @Feez2403 in #3139
• Clarify flag name in docs/nerfology/methods/splat.md by @EliasWatson in #3140
• bump version to 1.1.0 by @jb-ye in #3143

New Contributors

• @hardhat5 made their first contribution in #3054
• @dberga made their first contribution in #3065
• @codeprimate made their first contribution in #3018
• @Satvik1701 made their first contribution in #3067
• @carlinds made their first contribution in #3103
• @Leandropassosjr made their first contribution in #3125
• @Feez2403 made their first contribution in #3139
• @EliasWatson made their first contribution in #3140

Full Changelog: v1.0.3...v1.1.0

v1.0.3

What's Changed

• splatfacto-big by @AdamRashid96 in #2945
• Support new MPS filenames for Project Aria point clouds by @brentyi in #2949
• Show viewer resolution as WxH instead of HxW by @brentyi in #2948
• Fix Nerfacto + Aria by @brentyi in #2950
• Fix progress bar for full images datamanager by @brentyi in #2969
• fix bug that opacity compentation not being applied to depth raterization by @jinhwanlazy in #2966
• add splatfacto-big docs by @AdamRashid96 in #2955
• Adding Terminal Window to Jupyter Cells so all Colab users (free and pro) can train with Nerfstudio by @AntonioMacaronio in #2870
• Refactor splatfacto gaussian params with a ParameterDict by @kerrj in #2946
• doc: fix code typo in 'NeRF' method doc by @Crescent-Saturn in #2978
• Fix depth-nerfacto edge cases by @ethanweber in #2939
• Handle alpha images properly for instant-ngp and tensorf models by @trinh31201 in #2979
• Fix: Masks having wrong dimension after undistortion (causes crash in splatfacto) by @Zunhammer in #2987
• Camera models by @wooni-github in #2997
• Add 'within' function to SceneBox by @tobiasfshr in #2991
• enable coarse-to-fine training by @jb-ye in #2984
• Upgrade to latest nbformat 5.9.2 by @ringohoffman in #2964
• Make ply export property ordering backward compatible (fixes #3004) by @mathijshenquet in #3005
• Fix rotation_matrix for opposite float32 vectors by @jb-ye in #3011
• Fix bug when trying to create a camera path in viewer by @MildMystery in #3016
• Support rectangle selection in viewer by @chungmin99 in #3014
• Get rid of redundant projection matrix computations in Splatfacto (needs a gsplat update) by @oseiskar in #3019
• Exporting Splatfacto: correct errors when there are NaN/Inf values in some attributes by @MaximeVandegar in #3032
• Fix core tests with Pillow>=10.3.0 by @jb-ye in #3034
• Support COLMAP reconstructions with non-flat image dirs by @zacstewart in #3006
• bump version to 1.0.3 by @jb-ye in #3035

New Contributors

• @Crescent-Saturn made their first contribution in #2978
• @trinh31201 made their first contribution in #2979
• @wooni-github made their first contribution in #2997
• @mathijshenquet made their first contribution in #3005
• @MildMystery made their first contribution in #3016
• @MaximeVandegar made their first contribution in #3032
• @zacstewart made their first contribution in #3006

Full Changelog: v1.0.2...v1.0.3

v1.0.2

What's Changed

• fix: pixelated downscaled images by @ymtoo in #2866
• Add multi-processing support for cache_image. Fixed the issue of insufficient precision leading to a completely black image when converting from RGBA to RGB. by @KevinXu02 in #2867
• Enable always returning depth for Gaussian Splatting by @ethanweber in #2873
• Update viewer legacy docs by @brentyi in #2875
• Add default depth output when no gaussians visible by @chungmin99 in #2874
• Remove useless call to .with_suffix(""), which causes a bug if filename contains dots by @f-dy in #2882
• support generic TDataset in paralleldatamanager by @hturki in #2884
• [Fix] convert camera_idx to tensor by @tobiasfshr in #2890
• Fix benchmarking script camera optimizer argument by @gchhablani in #2899
• add zipnerf-pytorch as external method by @Jing1Ling in #2850
• Add transparency carving to splatfacto by @pa-la in #2889
• Fix an issue where gradient accumulation could not be passed as argument due to a type error. by @SharkWipf in #2910
• Implement new rasterization mode using opacity compensation factor by @jb-ye in #2888
• Switch default matching method for videos to 'sequential' in COLMAP by @kerrj in #2912
• Call rescale_output_resolution before early return by @pierotofy in #2897
• Make time slider effective in viewer (Fixes #2928) by @iSach in #2931
• Fixed ns_render dataset bug in splatfacto by @pa-la in #2917
• Update project, rasterize with block_width interface by @kerrj in #2937
• Full implementation of features for dynamic scenes into the Viser viewer. by @iSach in #2936
• fix crash when both mask and downscale_factor are set by @jinhwanlazy in #2920
• 1.0.2 by @kerrj in #2943

New Contributors

• @gchhablani made their first contribution in #2899
• @Jing1Ling made their first contribution in #2850
• @pa-la made their first contribution in #2889
• @jinhwanlazy made their first contribution in #2920

Full Changelog: v1.0.1...v1.0.2

v1.0.1

Bug fixes!

What's Changed

• important fix typo by @jb-ye in #2800
• Add documentation on existing datasets by @VasuAgrawal in #2806
• Update splatfacto.py by @Harr7y in #2804
• Fix typo in parallel_datamanager.py by @eltociear in #2812
• Make downloading more windows-friendly by @VasuAgrawal in #2810
• Have Mill19 dataset use official splits by default by @hturki in #2745
• Fix mask shape for Fisheye624 cameras by @brentyi in #2813
• Use packaging for colmap version by @chungmin99 in #2814
• Remove viewer build badge by @brentyi in #2819
• Add alpha rendering to splatfacto, fix depth bug by @kerrj in #2824
• Fix "mutable default" error in render.py by @pyetras in #2825
• fixing colmap installation to use apt-get since gdown on the URL unable to download colmap by @AntonioMacaronio in #2823
• Update viewer docs by @brentyi in #2826
• Fix the background color bug when exporting video with the "random" background option by @KevinXu02 in #2831
• External Method: seathru_nerf by @psetinek in #2829
• Add support for loading 3D points with ODM data processor by @pierotofy in #2838
• Add average_init_density to improve robustness of nerfacto training by @jb-ye in #2834
• Mask flexibility for methods than need to sample in the masked region by @ethanweber in #2647
• Add flag to disable apperance embedding by @jkulhanek in #2843
• Fix #2843 - safer typing by @jkulhanek in #2848
• limit torch to <=2.1 to avoid type errors by @kerrj in #2857
• Have predicted depth as expected_depth so gradients can be computed by @mattstrong-stanford in #2852
• Avoid OOM for caching undistorted images of splatfacto by @jb-ye in #2855
• Replace depth alpha mask logic with torch.where for gradients in splatfacto by @kerrj in #2856
• Changed torch version to <2.2 by @simonbethke in #2861
• Fix ODM data processor coordinate system by @pierotofy in #2847
• Upper-bound torch version for dev installs only by @brentyi in #2864
• v1.0.1 by @tancik in #2865

New Contributors

• @Harr7y made their first contribution in #2804
• @pyetras made their first contribution in #2825
• @AntonioMacaronio made their first contribution in #2823
• @psetinek made their first contribution in #2829
• @mattstrong-stanford made their first contribution in #2852
• @simonbethke made their first contribution in #2861

Full Changelog: v1.0.0...v1.0.1

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 https:...

v0.3.4

What's Changed

• Nerfstudio Feedback Form by @ethanweber in #2351
• Optimizers.scheduler_step() bug fix by @JADGardner in #2352
• Switching Nerfstudio Dataset data to GDrive URLs by @ethanweber in #2358
• Added a pytorch implementation of OmniCV's to remove equilib package usage by @THE-COB in #2350
• save sfm depth as png to keep 16bit. save depth_file_path as relative… by @zhan-xu in #2317
• Fix the starting command of docker. by @xjli360 in #2357
• Enable SparseNerf depth ranking loss to be used with GT/Sensor depth by @alexsax in #2312
• Fix: typo in PairPixelSamplerConfig's description by @elenacliu in #2372
• Fixes crop background color override by @kerrj in #2373
• cast background to device by @Mxbonn in #2381
• Fixes ARG before FROM bug by @padeler in #2371
• NERFSTUDIO_METHOD_CONFIGS callable MethodSpecification by @drewgilliam in #2385
• test_train tmp_path by @drewgilliam in #2400
• engine docs by @drewgilliam in #2405
• Fix the problem that camera will be freezed when moving forward by @yzslab in #2404
• Flesh out viewer beta by @kerrj in #2086
• Unify dataparser and method discovery by @jkulhanek in #2398
• camera/plugin docs by @drewgilliam in #2412
• Fix issue when extracting all frames from a video. by @SharkWipf in #2413
• Allow colmap parser to load 3D points by @jkulhanek in #2408
• Rename COLMAP 3D point features by @jkulhanek in #2417
• Fix benchmarking: apply get_background_color in renderer and set profiler to none by @Mxbonn in #2397
• Colmap parser: fix downscale for complex paths by @jkulhanek in #2425
• fix pixel sampling with masks issue when data is list by @anc2001 in #2369
• Add Comet Logging by @sherpan in #2431
• Fix import error when tcnn installed but CUDA runtime not available by @jkulhanek in #2429
• Allow the option for timestamp to be generated for ns-train --load-config by @kobejean in #2442
• Add share link support for beta viewer by @brentyi in #2445
• Render oriented crops in viewer beta by @kerrj in #2447
• Disable loading colmap points by default by @jkulhanek in #2451
• v0.3.4 by @tancik in #2452

New Contributors

• @zhan-xu made their first contribution in #2317
• @xjli360 made their first contribution in #2357
• @Mxbonn made their first contribution in #2381
• @padeler made their first contribution in #2371
• @drewgilliam made their first contribution in #2385
• @anc2001 made their first contribution in #2369
• @sherpan made their first contribution in #2431
• @kobejean made their first contribution in #2442

Full Changelog: v0.3.3...v0.3.4

v0.3.3

Highlights

• Faster downscaling during image processing
• VR180 rendering
• nerfacto alpha transparency training
• Sparse-NeRF depth losses
• New template repo for implementing new methods
• Bug fixes

What's Changed

• Add examps to generfacto docs by @terrancewang in #2120
• Fix get_num_frames_in_video by @olegpokhilchenko in #2090
• Update nerfacto.md by @tancik in #2126
• Fix pickling of VanillaDataManager by @jkulhanek in #2129
• Jkulhanek/colmap dataparser by @jkulhanek in #2115
• Update generfacto.md by @tancik in #2132
• Fix to fall back to torch if tcnn not found by @ethanweber in #2124
• allow ns-process-data to use CR2 raw images by @machenmusik in #2119
• Fix unnecessary encodings calculation in tensorf field by @kst179 in #2145
• Remove breakpoint from colmap_dataparser by @jkulhanek in #2141
• Add option to render evaluated images by @hturki in #2135
• Fix typo in nerfacto.py by @MvWouden in #2149
• add build-arg cuda version to dockerfile by @Ilyabasharov in #2139
• Fix use_appearance_embedding for instant-ngp by @brentyi in #1999
• Default to tcnn by @tancik in #2159
• make all SDFFieldConfig params configurable via constructor by @decrispell in #2167
• Correct path notation for Windows in documentation by @KaerMorh in #2171
• Fix image saving format issue in render by @colin-de in #2172
• fix the ZeroDivisionError occured in int(image_width / aspect_ratio) when aspect_ratio equals zero by @WebGao in #2177
• Remove pytorch hash table if tcnn implementation is used by @georghess in #2175
• Feature/run_beta_viewer by @Ilyabasharov in #2157
• Avoid zero duration crash by @machenmusik in #2193
• Fixing Colmap VocabTreeMatching command to support spaces in Filename by @JDihlmann in #2195
• Default fied_heads with instances will cause shared parameters by @hyperzy in #2197
• Pin versions of pyceres+pixsfm, up pycolmap by @skydes in #2199
• Adding input handling for RFFEncoding's get_out_dim(self) by @CardiacMangoes in #2201
• Fix colmap vocab_tree_path (#2195) to work with Windows by @machenmusik in #2204
• Add saving/loading scheduler state_dict by @hyperzy in #2203
• Omnidirectional Stereo Update - Alignment and Compositing by @cvachha in #2217
• Reorient point cloud normals for better surface reconstruction by @NotAGoose in #2220
• Try non-strict model loading on RuntimeError. ... by @sjuxax in #2214
• Add documatations for TensoRF by @Xzzit in #2209
• Fast downscaling for video and image processing (PR2168 plus images) by @machenmusik in #2213
• refactor: get_normalized_directions by @SauravMaheshkar in #2216
• Update torchmetrics by @tancik in #2223
• Remove superfluous -r1 (fix ffmpeg/colmap video) by @SharkWipf in #2231
• Fix arguments that are not passed from config to NerfactoField by @liu115 in #2186
• Minor kwarg fix to be future-compatible with viser version by @kerrj in #2235
• Add std for eval by @Khoa-NT in #2239
• Implement nerfacto alpha transparency training by @nepfaff in #2165
• Load schedulers from ckpt in a backward-compatible manner by @hyperzy in #2236
• support packed samples in semantic renderer by @hturki in #2247
• Render VR180 video by @cvachha in #2261
• nerfbusters doc by @FrederikWarburg in #2208
• Use correct pixel area in volumetric sampler by @hturki in #2268
• ns-render with depth colormap support by @ethanweber in #2125
• Update index.md by @tancik in #2279
• Moved Volinga as an external method by @Frivas97 in #2282
• Add depth_unit_scale_factor to sdfstudio_dataparser by @alexsax in #2285
• Option to process images on GPU for speed at the expense of memory by @AX-I in #2288
• More robust install instructions by @brentyi in #2277
• Remove system-level CUDA install from install instructions by @brentyi in #2289
• Monodepth Regularization by @ethanweber in #2284
• Allow same dimensions optimizations to be disabled by @machenmusik in #2292
• convert raw to JPG not TIFF, to avoid fast-downscale ffmpeg error by @machenmusik in #2295
• Train and eval data splits (Nerfbusters) by @FrederikWarburg in #2207
• PixelSampler Fixes by @AdamRashid96 in #2298
• Add sponsors by @tancik in #2307
• Adding support for PairPixelSampler and PatchPixelSampler masks by @ethanweber in #2305
• template repository by @maturk in #2319
• When generating depth images, use torch_compile with ZoeDepth for compatibility by @machenmusik in #2303
• Rename num_cameras to camera_indices by @maturk in #2326
• Ddp docs by @yurkovak in #2332
• fix: Allow custom user ID by @yurkovak in #2334
• fix: ColmapDataParser downscaling images error. by @onpix in #2337
• fix #2318: add train/test/eval split for instant ngp dataparser by @elenacliu in #2335
• Circle crop to images processing pipeline by @kerrj in #2341
• viser 0.1.0, fix type checker errors by @brentyi in #2343
• Update pixel_samplers.py by @alexsax in #2327
• v0.3.3 by @tancik in #2349

New Contributors

• @olegpokhilchenko made their first contribution in #2090
• @kst179 made their first contribution in #2145
• @Ilyabasharov made their first contribution in #2139
• @KaerMorh made their first contribution in #2171
• @WebGao made their first contribution in #2177
• @georghess made their first contribution in #2175
• @JDihlmann made their first contribution in #2195
• @hyperzy made their first contribution in #2197
• @skydes made their first contribution in #2199
• @CardiacMangoes made their first contribution in #2201
• @NotAGoose made their first contribution in #2220
• @sjuxax made their first contribution in https://github.com/nerfstudio-project/nerfstudio/pu...

v0.3.2

Highlights

• Add nerfacto-huge model
• Add text-to-3d model generfacto
• Support for CPU and M1/M2
• Support for rendering omni-directional stereo video
• Bug fixes

What's Changed

• Update installation docs by @tancik in #1970
• generalize mask collation to other image-like data by @decrispell in #1959
• fix large number of typos in repository by @MvWouden in #1977
• Basic viser frontend by @tancik in #1973
• Add warnings for (slower) Torch 1.x and Windows not supporting torch.compile by @jkulhanek in #1982
• Added at_train_end logic to base pipeline by @maturk in #1932
• Bump socket.io-parser from 4.2.1 to 4.2.3 in /nerfstudio/viewer/app by @dependabot in #1983
• fix visualize encoding bug by @SophusDavid in #1984
• Fix Viewer Recursion: StackOverflow in Server Setup by @lukasHoel in #1987
• Fix custom dataparser docs by @tancik in #1991
• style(ruff): provide better integration with ruff vscode extension by @SauravMaheshkar in #1994
• Fix viewer decorator by @tancik in #1995
• SIGGRAPH 2023 Citation Update by @ethanweber in #1997
• add deepfloyd model by @terrancewang in #1993
• pass grad scaler from trainer to pipeline by @terrancewang in #1996
• Fix exponential decay warmup by @tancik in #2002
• Ability to use vanilla pytorch instead of tcnn for Nerfacto by @ethanweber in #1936
• Fixes wandb runs resuming using WANDB_RUN_ID by @jkulhanek in #2004
• add controls to the beta viewer by @tancik in #2005
• Render Omni-directional stereo video (360 3D VR) by @cvachha in #1986
• Bump tyro by @brentyi in #2008
• Add Metadata Handling to Cameras Collation Function by @MingwuZheng in #2001
• [WIP] Fix model loading collate_fn non-static by @jkulhanek in #1990
• Colab update to Python 3.10 by @akristoffersen in #2017
• Update metashape_utils.py by @henrypearce4D in #2011
• Add antialias parameter as default None by @maturk in #2033
• installation.md: Use https instead of ssh for git clone. by @SharkWipf in #2030
• Add option for model normals on ply export by @CameronFraser in #1965
• Fix Typo on colab file by @Bishadkoju in #2039
• Fix bug when copying images when input_dir = output_dir by @maturk in #2041
• Reduce GPU memory usage in CacheDataloader by @jkulhanek in #1730
• Quick fix for eval script failing for depth-nerfacto (and other methods with a non-standard dataset) by @jMysliwiec in #2047
• Fix metashape multiple camera models error message by @henrypearce4D in #2057
• Add kwargs to dataparser outputs by @maturk in #2053
• nerfstudio dataparser: avoid loading images at inference time by @f-dy in #2051
• fix for scannet dataset camera pose loading by @colin-de in #2056
• colormaps: add "gray" by @f-dy in #2058
• Move out NeRFPlayer: clean files and add method link by @lsongx in #2072
• Update data_utils doc by @tancik in #2076
• nerfacto-huge by @kerrj in #2003
• reduce nerfacto-huge memory by @kerrj in #2082
• Fix data downscale paths by @tancik in #2071
• don't force downscale factor to 1 for nerfacto-huge by @machenmusik in #2088
• Fix resolution rendering logic in statemachine for viewer beta by @kerrj in #2085
• [WIP] dreamfusion implementation by @terrancewang in #1008
• add gradient accumulation support by @ksnzh in #2049
• Add non-trainable camera indices to CameraOptimizer by @maturk in #2080
• Update nerfacto.md by @Shiva-Gantha in #2107
• Add option to process masks on GPU for speed at the expense of memory by @machenmusik in #2110
• Fixing the image_dir if using skip_image_processing by @Khoa-NT in #2111
• Allow newer pycolmap for newer python by @jkulhanek in #2113
• Fix spherical harmonics #2081 by @jkulhanek in #2112
• Fix quickstart doc for remote host viewing setup by @jlightfoot in #2101
• v0.3.2 by @tancik in #2118

New Contributors

• @MingwuZheng made their first contribution in #2001
• @SharkWipf made their first contribution in #2030
• @CameronFraser made their first contribution in #1965
• @Bishadkoju made their first contribution in #2039
• @jMysliwiec made their first contribution in #2047
• @colin-de made their first contribution in #2056
• @Shiva-Gantha made their first contribution in #2107
• @Khoa-NT made their first contribution in #2111
• @jlightfoot made their first contribution in #2101

Full Changelog: v0.3.1...v0.3.2

Code release for SIGGRAPH 2023 paper.

This branch exists for historical purposes. It was used to generate the numbers in the SIGGRAPH paper. We don't plan on integrating this code into the main branch, but it can exist here as a reference or for reproducing our results. We view nerfstudio as an active repo with continual contributions, and some of these changes are undesirable for the main branch (e.g., how we deal with appearance embeddings for evaluation). This is done in an effort to keep our repo extensible for further changes.

Update Aug 29, 2023 - We are deprecating the URL used to host the data from processing MipNeRF-360 with ns-process-data. You can now find it on Hugging Face here. Or, you can replicate the steps described in our paper or use a different MipNeRF-360-specific data parser and use their COLMAP reconstructions directly.

v0.3.1

##Highlights

• Fix compatibility with Windows

What's Changed

• Remove hloc from pyproejct by @tancik in #1955
• Update render docstring by @tancik in #1960
• Backward compatibility for torch 1.x and fix for windows by @jkulhanek in #1962
• Report tcnn import errors by @tancik in #1969
• Fix mask check in PatchPixelSampler by @lukasHoel in #1971
• v0.3.1 by @tancik in #1972

New Contributors

• @lukasHoel made their first contribution in #1971

Full Changelog: v0.3.0...v0.3.1