Commit Graph
810 Commits
Author SHA1 Message Date
Gina WuandJustin Kerr c3bcee89a3 Bump viser (#3234)
* Bump viser to 0.2.2
---------

Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
2024-06-28 13:27:19 -07:00
Tamir CohenandJustin Kerr 1af71f2fff Fix parsing of non ascii image names in colmap's images.bin (#3256)
Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
2024-06-28 19:50:35 +00:00
Zhensheng Yuan df57a8db72 Fix different initial tension value between tension_slider and `cam… (#3271)
* Fix different initial tension value between `tension_slider` and `camera_path.tension`

* Fix ruff check
2024-06-28 12:31:26 -04:00
Justin Kerr d6df39b70d Compatibility for numpy 2.0 (#3265)
* compat for numpy 2.0

* lint changes
2024-06-28 08:07:10 +09:00
Congrong Xu 3d27dd4609 Add descriptions for splatfacto-big and nerfacto-huge (#3233)
Update method_configs.py
2024-06-16 15:38:30 -04:00
Alex Jean 2e3c3c179a Background device (#3219)
added to(self.device) for background_color when in eval mode for splatfacto
2024-06-13 14:57:46 +03:00
Congrong Xu 290f3fa028 Adds back screen size too bigs culling as an option (#3211)
* revert too bigs

* format

* remove squeeze(0)

* add if not training to the bg expand logic
2024-06-12 17:29:36 +00:00
Ruilong Li(李瑞龙)andRuilong Li 4b61cb9e6d Fix bug in SplatfactoModel when sh_degree is zero the color is not with sigmoid (#3207)
* torch.compile -> torch_compile from misc

* sigmoid on color when sh_degree==0

---------

Co-authored-by: Ruilong Li <397653553@qq.com>
2024-06-10 13:39:36 -07:00
Simon Fraser d220600b8b Making install_checks use colmap_cmd (#3204)
check_colmap_installed() in nerfstudio.utils.install_checks.py previously didn't use the colmap_cmd attribute of ColmapConverterToNerfstudioDataset. This change addresses that so an alternative colmap_cmd can actually be used
2024-06-09 20:35:30 -07:00
Ruilong Li(李瑞龙)andRuilong Li 36187d5224 torch.compile -> torch_compile from misc (#3202)
Co-authored-by: Ruilong Li <397653553@qq.com>
2024-06-08 15:18:15 -07:00
b6d0ca00dd Update splatfacto with gsplat 1.0 (#3200)
Co-authored-by: Ruilong Li <397653553@qq.com>
Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
2024-06-08 11:40:06 -07:00
isrishandJ.Y 6c51e589bd Adding new captures to eyeful dataset (#3186)
* Update eyeful_tower.py

Added two new captures to eyefultower dataset.

* Update eyeful_tower.py

---------

Co-authored-by: J.Y <132313008+jb-ye@users.noreply.github.com>
2024-06-06 17:56:15 +00:00
e58d513942 Generalize get average image metrics (#3188)
generalize get average image metrics

Co-authored-by: Le Hoanh <leh19@csl-leh19.cs.aalto.fi>
Co-authored-by: J.Y <132313008+jb-ye@users.noreply.github.com>
2024-06-06 17:52:02 +00:00
J.YandJianbo Ye 883d64996b Introduce FPSampler for train cameras (#3177)
* Introduce FPSampler for train cameras

* improve document and log

---------

Co-authored-by: Jianbo Ye <jianboye@amazon.com>
2024-06-06 17:34:59 +00:00
Otto Seiskari 5491df92d9 Export Splatfacto-optimized poses (#3116)
* Fix exported poses when Splatfacto pose optimization is enabled

Currently works correctly only with --eval-mode=all

* Make Splatfacto pose adjustments consistent with Nerfacto

Also allow exporting Nerfacto-optimized poses. Fixes #3073.
Second revision where the rotation and translation parts
are handled separately.
2024-05-29 10:08:54 -04:00
SerenitysmkandJ.Y 12f2e681a4 Fix: when --use-sfm-depth is enabled and the model is given by --colm… (#3172)
Fix: when --use-sfm-depth is enabled and the model is given by --colmap-model-path. It searches the wrong reconstruction directory

Co-authored-by: J.Y <132313008+jb-ye@users.noreply.github.com>
2024-05-28 15:08:20 -04:00
Siming He 67d9fd1933 NeRFtoGSandBack (#3150)
* add methods

* fix reference in index.md

* update description
2024-05-27 17:29:26 +03:00
Anthony ZhangandJ.Y 456930c213 Fixing resize_image and adding additional distortion check (#3162)
adding fixes for the runtime error on masking as well as distortion checking

Co-authored-by: J.Y <132313008+jb-ye@users.noreply.github.com>
2024-05-24 23:31:45 -04:00
5a341eac2c Fix "poster" dataset extraction (#3164)
Co-authored-by: Martin Mokry <martin-kokos@users.noreply.github.com>
Co-authored-by: maturk <30566358+maturk@users.noreply.github.com>
2024-05-24 15:12:44 +03:00
paolovic 742963e073 remove redundant code in full_images_datamanager.py (#3155)
remove redundant code
2024-05-22 12:51:19 -04:00
Congrong Xu e6d780d2a0 Only import pycolmap in run_hloc (#3146)
* remove pycolmap import on windows

* only import when run hloc

* also for pixsfm

* fix
2024-05-15 11:33:46 -04:00
George Tang ddcbb5c7f8 Fix legacy tensor construction (#3145) 2024-05-14 10:42:23 -07:00
Feez2403 ffbd16a375 Fix edge case of depth colormap (#3139)
If the user sets near_plane as 0.0, the "or" will take the second term (float(torch.min(depth))) instead of using the 0.0 value.  We fix this by checking explicitely for a "None" variable
2024-05-11 21:38:13 -04:00
J.YandJianbo Ye a4c32ada52 Make RealityCapture csv/ply exports work! (#3131)
* support ply input file for ns-process-data realitycapture


Co-authored-by: Jianbo Ye <jianboye@amazon.com>
2024-05-09 08:58:03 -07:00
c17d1d7315 Add kwargs handling for patchpixelsampler patch size (#2622)
* Add kwargs handling for patchpixelsampler patch size

* Run black

---------

Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
Co-authored-by: J.Y <132313008+jb-ye@users.noreply.github.com>
2024-05-08 10:45:58 -07:00
Leandro Passos 9fe8e6c27c BioNeRF (#3125)
* bionerf markdown file

* method description in markdown file

* inserting bionerf in index file

* bionerf description

* fixing image paths

* including results on readme

* deleting last line from bionerfs page
2024-05-06 22:11:07 -07:00
Justin Kerr 3096f445b8 Add a pointcloud export from polycam to process-data (#3124)
* add a pointcloud export from polycam mesh to process-data

* bugfix
2024-05-06 14:40:05 -07:00
hturki f2a73804d4 fix nerfstudio collate function (#2965)
* fix nerfstudio collate function

* run ruff

* address PR feedback
2024-05-06 13:37:42 -04:00
49f5934ab3 Support splatfacto training for metashape exports (#3122)
* Added the possibility to import a metashape ply file

* FIxed double import and import order

* Ruff Format

* Ruff Format

* Ruff Format

* Ruff SUCKS

* make ply as an option and use applied_transform

* fix ruff

* fix bugs when ply doesn't exist

* fix bugs when ply doesn't exist

* no backtrace for ValueError

* hot fix

* Add return type

---------

Co-authored-by: simonbethke <simon.bethke@gmail.com>
Co-authored-by: Jianbo Ye <jianboye@amazon.com>
Co-authored-by: Brent Yi <yibrenth@gmail.com>
2024-05-01 21:24:33 -04:00
J.Y 3c4c3ae07e Fix #3064 and some minor changes (#3121) 2024-05-01 12:43:41 -07:00
e232227e31 metashape_utils: work with camera groups (#2626)
* metashape_utils: work with camera groups

* metashape_utils: console message when skipping a camera due to a missing image

---------

Co-authored-by: Frédéric Devernay <f-dy@users.noreply.github.com>
Co-authored-by: J.Y <132313008+jb-ye@users.noreply.github.com>
2024-04-30 20:25:59 +00:00
Carl Lindström 759fda8285 Fix bug in pixel sampler (#3103)
* Fix bug in pixel sampler

* Refactor code for distributing rays across images
2024-04-30 09:57:20 -04:00
b190874ef1 Use AbsGrad to get better results with less gaussians (#3113)
* Use AbsGrad to get better results with less gaussians

* some adjustment such that splatfacto-big don't go OOM

* use new gsplat version

---------

Co-authored-by: Jianbo Ye <jianboye@amazon.com>
Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
2024-04-29 16:32:48 -04:00
Mathijs Henquet bc9328c7ff GaussianSplats export: allow uint8 in ply (#3111)
* GaussianSplats export: allow uint8 in ply

* Ruff formatting

* Add test and narrower typing

* Formatting

* Revert narrow typing, not supported by old python

* Fix typing for old pythons
2024-04-29 14:30:25 -04:00
Rohan MathurandJustin Kerr f046ceadf6 Adding cropping for gaussian splat exports (#3105)
* added bounding box to splat export params

Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
2024-04-29 17:05:49 +00:00
Satvik SharmaandJustin Kerr 3f39546653 Adding lock for Viser Element callbacks (#3067)
* add callback lock, prepare for testing

Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
2024-04-25 23:35:24 -07:00
dbergaandJianbo Ye db93476b6a Hloc fix for image_ids (camera per image) (#3081)
* changed run_hloc args to fill image_ids (added image_list and changed camera_mode to PER_IMAGE)

* added parameter same_camera on ns-process-data for multifocal cases in hloc. Also updated colmap_to_json to detect if there is one or several cameras per frame while keeping the camera type specifications

* ruff-formatted changes in colmap_utils.py

* use_single_camera_mode update args, including colmap_utils and hloc_utils

* changed multicamera warning's print to CONSOLE.print

* fix path typo console print

* rewritten use-single-camera-mode comment in ns-process-data

* (fix) inverted bool for colmap_utils

* change im_id to im_data.camera_id

---------

Co-authored-by: Jianbo Ye <jianboye@amazon.com>
2024-04-24 12:43:45 -04:00
J.YandJustin Kerr d9b022b25f Allow alpha transparency training for blender datasets input (#3088)
Allow alpha transparency training for rgba input

Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
2024-04-19 18:03:55 +00:00
Congrong XuandBrent Yi eddf2d21b5 Changes for trainer.py to support the Gradio webui (#3046)
* changes for trainer to support webui

* Update trainer to support webui

* format

* add a seperated shutdown() function to stop training

* typo fix

* get rid of _stop_viewer_server()

* Update trainer.py

* organize import

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
2024-04-19 00:37:50 +00:00
Justin Kerr 45d8bb79ea updates to apply_pca_colormap (#3086)
* improvements to pca_colormap: allow input pca matrix, optional ignore_zeros arg

* typo
2024-04-17 23:54:43 -07:00
Patrick Morgan babf57718c Fix call to detect ODM reconstruction file (#3018) 2024-04-12 21:23:47 +00:00
Justin Kerr a64026f8db shift principle points by .5 in undistortion (#3071)
* shift principle points by .5

* fix ordering

* add fisheye offset
2024-04-12 15:32:22 -04:00
Gunjan ChhablaniandBrent Yi c302cc5301 Add pointcloud loading for blender parser (#2902)
* Add pointcloud loading for blender parser

* Fix argument

* Fix docstring

* Fix metadata in dataparsers

* Add changes from review

* Avoid changing default behavior

* Apply `scale_factor` to loaded points

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
2024-04-11 13:41:14 -07:00
hyperzy 03bdeff2ad Fixed Unexpectedly huge RAM consumption of parallel datamanager (#3060)
* Reduced the memory usage by caching image after the datamanager process starts
2024-04-11 18:56:37 +00:00
J.Y 4714ae75f7 write eval combined images for diagnostics (#3070) 2024-04-11 18:37:02 +00:00
Otto Seiskariandjh-surh eba72db22a Camera pose optimization for Splatfacto (#2891)
* Add pose optimization to Splatfacto

* Disable Splatfacto pose optimization by default

* Improve apply_to_camera for Gaussian Splatting pose optimization

Do not chain modifications to camera_to_worlds to improve
numerical stability and enable L2 rot/trans penalties.

* Add separate mean and max rot/trans metrics to camera-opt

* Tweak pose optimization hyperparameters

Parameters used in the Gaussian Splatting on the Move paper v1

* Unit test fix for new cameara_optimizer training metrics

* Adjust splatfacto-big camera pose optimization parameters

Same parameters as in normal Splatfacto

---------

Co-authored-by: jh-surh <jh.surh@bucketplace.net>
2024-04-11 14:23:17 -04:00
dbergaandBrent Yi 2d9bbe5091 fix exporter.py for FullImageDataManager and RandomCamerasDataManager (#3065)
* fix exporter.py for FullImageDataManager and RandomCamerasDataManager

* sort imports

* ruff

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
2024-04-11 02:04:33 +00:00
Justin KerrandBrent Yi c381fc818d Fix custom elements nested under @property (#3066)
* patch custom elements bug

* Skip `cached_property`

* fomrat

* comment, type hint

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
2024-04-10 18:59:20 -07:00
Saurav MaheshkarandBrent Yi d1fc2ee338 feat(ci): migrate to uv in CI (#3038)
* feat(ci): migrate to `uv` in CI

* feat(ci): drop upgrade strategy

* feat(ci): use `uv` in docs workflow

* fix(ci/doc): update sphinx build cmd

* fix(ci/doc): specify python path

* (experimental) simplify

* remove venv

* Revert line wrap change for doc.yml

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
2024-04-08 15:46:00 -07:00
Sahil Jain 2b9171528b Fix config loading for Eyeful Tower dataset (#3054)
Add test_filenames to transforms.json generated by eyeful_tower.py
2024-04-08 17:04:20 +00:00