tink/nerfstudio
4
0 Fork 0
mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-12 02:45:34 +08:00
Code Activity
1,351 Commits 85 Branches 40 Tags
v0.1.19
Commit Graph
1351 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Matthew Tancik 7ae2fce52b v0.1.19 (#1585) v0.1.19 2023-03-10 18:10:33 -08:00
Matthew Tancik 63af268495 Remove webrtc (#1579) 
* Remove webrtc

* cleanup

* lint

* cleanup

* Lower quailty

* Update viewer version

* Update docs

* remove cryptography req
 2023-03-10 12:00:35 -08:00
Frédéric DevernayandFrédéric Devernay a277cd4886 camera_utils: add "vertical" orientation and "focus" center methods (#1543) 
* camera_utils: add "vertical" orientation and "focus" center methods

* camera_utils: -Z is the look-at direction

* Update nerfstudio_dataparser.py

* missing import

* fix pylint issues

* camera_utils: handle degenerate case for "vertical" orientation method

* camera_utils: split focus_of_attention computation

---------

Co-authored-by: Frédéric Devernay <f-dy@users.noreply.github.com>
 2023-03-10 11:22:21 -08:00
Matthew Tancik 510188b1e6 Revert "MinimalDataParser add options, allow Nerfstudio data format to specify test indices" (#1583) 
Revert "MinimalDataParser add options, allow Nerfstudio data format to specify test indices (#1541)"

This reverts commit c61d3e9387.
 2023-03-10 10:23:17 -08:00
Frédéric DevernayandFrédéric Devernay 21a452f1b4 scripts/exporter.py: export PLY compatible with PCL (#1572) 
* scripts/exporter.py: export PLY compatible with PCL

Use the newer Open3D Tensor API to write pointclouds as float32, which
are compatible with PCL (see https://github.com/isl-org/Open3D/issues/1633).

fixes https://github.com/nerfstudio-project/nerfstudio/issues/1571

* exporter.py: pylint: disable=no-member

fixes https://github.com/nerfstudio-project/nerfstudio/actions/runs/4377569585/jobs/7661246358#step:10:13

open3d.core.Dtype has been around since open3d 0.11.0 http://www.open3d.org/docs/0.11.0/python_api/open3d.core.Dtype.html

---------

Co-authored-by: Frédéric Devernay <f-dy@users.noreply.github.com>
 2023-03-10 10:20:36 -08:00
Alexander Kristoffersen 99afaa7164 Patch Sampling bug fix (#1578) 
quick fix.
 2023-03-09 17:30:41 -08:00
Matthew Tancik ba8f9b48a4 Remove regex for export path (#1577) 
* Remove regex for export path

* lint
 2023-03-09 13:29:13 -08:00
Dreek FireandMatthew Tancik 382ed853f2 Replace default colormap option with turbo for single-channel output (#1568) 
replace default colormap option with turbo for single-channel output

Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
 2023-03-09 13:24:04 -08:00
Rohan Mathur 403ab26f0c Changed percent-crop to crop-factor so it's less confusing (#1575) 
* changed percent-crop arg to crop-factor so it's more clear that it's a float

* added error if crop values are less than 0 or more than 1

* added value hint and changed error to console thing

* added imports

* fixed linter issues

* refixed linter issues
 2023-03-09 12:23:50 -08:00
Jonáš Kulhánek c61d3e9387 MinimalDataParser add options, allow Nerfstudio data format to specify test indices (#1541) 
* MinimalDataParser add options, allow Nerfstudio data format to specify test indices

* Switch from indices to filenames and add tests
 2023-03-09 19:14:24 +01:00
Rohan Mathur 1f8a07c10e Fixed percent crop typo (#1573) 
I put 20 instead of 0.2
 2023-03-08 19:39:27 -08:00
Jaldert Rombouts b66dc0c20c Correct instructions for Docker build (#1557) 
This fixes the instruction for the cuda-architecture specific Docker build.
 2023-03-08 07:47:43 -08:00
Rohan Mathur 9dc7fc2e44 Added documentation for equirectangular input (#1561) 
* added documentation for equirectangular

* fixed typo and mentioned 3fps is empirical
 2023-03-07 15:28:21 -08:00
Georgy Ponimatkin c0c714c831 Fix minor scannet bug. (#1555) 2023-03-05 17:34:38 +01:00
Loïc Magne 7b8999ac3d Fix typo in docs Nerfology/Model components/Ray samplers (#1553) 
fixed typo
 2023-03-03 09:56:37 -08:00
Rohan Mathur 982e527bee Added video cropping for equirectangular and made it independent of mask in normal videos (#1542) 
* started bottom crop functionality

* first draft of cropping

* cleaned up and debugged cropping equirectangular and re added mask stuff just without percent crop

* added nonequirectangular video crop

* added left right crop for equirectangular

* shortened equirect utils

* finished regular video cropping

* removed print, added underscores, changed type to List[float]
 2023-03-02 18:24:59 -08:00
Georgy Ponimatkin f48fa6a923 Instant ngp args (#1549) 
* Expand instant-ngp args.

* Fixed misplaced string.
 2023-03-02 23:49:30 +01:00
Matthew Tancik 8d41e522e3 Avoid loading entire dataset on GPU (#1551) 2023-03-02 14:32:27 -08:00
Matthew Tancik a36f33c5ee Update datamager docs (#1548) 2023-03-02 10:27:30 -08:00
Matthew Tancik 74d12a5542 Speed up point cloud export (#1547) 2023-03-02 10:14:20 -08:00
Georgy Ponimatkin 63f5c8a2c4 Fix camera transformations in ARKitScenes and ScanNet (#1544) 
* Update arkitscenes_dataparser.py

Fix camera coordinate system in ARKitScenes.

* Update scannet_dataparser.py

Fix camera coordinates in ScanNet.
 2023-03-02 09:28:18 -08:00
misza222 5c810521a5 Update nerf.md (#1546) 
Add useful info that it doesn't require GPU to execute
 2023-03-02 09:12:46 -08:00
Sacha Lewin 6912e7cde9 Fix crash when having no eval dataset and not using the viewer (#1537) 
Fixed crash when no eval imgs on wandb/tensorboard
 2023-03-01 15:02:41 -08:00
Georgy Ponimatkin 7366456835 Adding conversion to torch.float32 in get_interpolated_poses_many. (#1532) 2023-02-28 09:22:22 -08:00
Matthew Tancik bfaf11cd72 Remove dataparser dependency (#1529) 2023-02-27 18:32:40 -08:00
Georgy Ponimatkin 4a9764d3c4 Fixing data processing script when depth is not used (#1527) 
Update process_data.py

Fix image_id_to_depth_path = {} to image_id_to_depth_path = None
 2023-02-27 18:23:58 -08:00
Georgy Ponimatkin 2eda6b4523 Fix pose centering flag for ARKitScenes dataparser (#1528) 2023-02-27 17:30:53 -08:00
Saurav Maheshkar 258ee26983 feat(fields): Improve Type Hints (#1524) 
* feat(fields/tensorf_fields): Improve Type Hints

* feat(fields/base_field): Improve Type Hints

* feat(fields/density_fields): Improve Type Hints

* feat(fields/instant_ngp_field): Improve Type Hints

* feat(fields/nerfacto_field): Improve Type Hints

* feat(fields/nerplayer_nerfacto_field): Improve Type Hints

* fix(fields/nerplayer_nerfacto_field): add typing imports

* feat(fields/nerfplayer_ngp_field): Improve Type Hints

* feat(fields/nerfw_field): Improve Type Hints

* feat(fields/semantic_nerf_field): Improve Type Hints

* feat(fields/vanilla_nerf_field): Improve Type Hints

* fix(fields/nerfplayer/nerfacto_field): reorder imports

* fix(feilds): str -> FieldHeadNames

* fix: remove Optionals

* fix: add missing comma
 2023-02-27 13:22:56 -08:00
Koke_Cacao edb54602da Bug fix for SHRenderer() (#1526) 
The current SHRenderer does not apply the activation function correctly due to a typo. Now it's fixed.
 2023-02-27 10:40:17 -08:00
Jonáš Kulhánek 955497fcb2 Add weight-decay option to RAdam optimizer (#1525) 2023-02-27 09:21:00 -08:00
Georgy Ponimatkin 5d640bfcfd Dataparsers for ScanNet and ARKitScenes (#1514) 
* Adding dataparsers for ScanNet and ARKitScenes datasets.

* Fixing automatic width and height determination in ARKitScenes.

* Making arkitscenes_dataparser.py to pass pylint checks.

* Fixing docstring in arkitscenes_dataparser.py.

* Fixing function name in arkitscenes_dataparser.py.
 2023-02-26 16:29:57 -08:00
Saurav Maheshkar 4545dcb6b3 feat: improve type hints (#1515) 
* feat(plugins/registry): Improve Type Hints

* feat(exporter/texture_utils): Improve Type Hints

* feat(exporter/tsdf_utils): Improve Type Hints

* feat(cameras/camera_utils): Improve Type Hints

* feat(cameras/cameras): Improve Type Hints

* feat(cameras/rays): Improve Type Hints

* fix: add default value for device

* fix: ArrayLike type hint
 2023-02-26 12:22:45 -08:00
Jonáš Kulhánek 7309273d92 Add support for more colmap camera models in ns-process-data (#1500) 
* Add support for more colmap camera models in ns-process-data

* Fix bugs introduced in #1457
 2023-02-26 18:53:08 +01:00
Georgy Ponimatkin 7da588c5d2 Extending ns-render to support loop rendering using interpolated cameras (#1508) 
* Extending ns-render to support loop rendering using interpolated cameras.

* Adding docstring for render.py. Applying formating.

* Expanding docstrings for class. Renaming trajectory type.

* Removing mentions of loop from render.py.
 2023-02-26 09:30:19 -08:00
Matthew Tancik 3e005815cc Check that video path is correct (#1513) 2023-02-25 22:54:49 -08:00
Paul Wais 5c73766653 SFM: sfm-based depth, some breadcrumbs for pycolmap (#1457) 
* save

* save

* more cleanup

* save

* save

* update phototourism

* save

* works

* works

* cleanup

* cleanup

* lint

* python3 default

* cleanup
 2023-02-25 21:10:53 -08:00
Alexander Kristoffersen b62571d537 Colab tinycudann drive link updated. (#1512) 
* updated tinycudann drive link.

* updated tinycuda drive link
 2023-02-25 20:12:46 -08:00
Saurav Maheshkar 0b87c43d0d feat(engine): improve type hints (#1509) 
* feat(engine): improve type hints

* fix: add pylint ignore statement

* fix: order imports as per isort

* fix: update Optimizer setup return type

* feat: add new TORCH_DEVICE type
 2023-02-25 16:33:43 -08:00
Matthew Tancik 5158cc36ff Fix logic when using filename datasets (#1510) 2023-02-25 16:06:41 -08:00
Matthew Tancik 1916d9c85f Update ffmpeg comment (#1505) 
update ffmpeg comment
 2023-02-25 15:24:16 -08:00
Fernando Rivas-ManzanequeandMatthew Tancik 9053643932 Volinga model and NVOL documentation (#1486) 
* added volinga model to NeRFStudio

* Removed unused dependencies

* Modified dockerfile to match main

* Corrected typo in core_code_checks.yml

* Corrected typo in core_code_checks.yml

* updated test with Volinga

* Added conversion to NVOL documentation

* [WIP] Refactor documentation and removing Volinga config

* Volinga use existing NerfactoModelConfig

* Added Unreal Engine documentation to extensions

* removed unused field class import

* Updated docs

* Documentation ready

* Update Dockerfile

---------

Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
 2023-02-25 14:49:53 -08:00
Jingchen Ye 871eb0f7d3 Rename friends dataset to sitcoms3d (#1503) 
* Rename friends dataset with official name sitcoms3d

* Rename downloaded folder

* Fix pylint
 2023-02-25 14:38:23 -08:00
Ruilong Li(李瑞龙) 7dc7129cf8 fixes for nerf synthetic dataset (#1507) 
* fixes for nerf synthetic dataset

* restore eval script

* fix format with black
 2023-02-25 14:37:10 -08:00
Saurav Maheshkar 92c9cee4c7 feat(docker): Add opencontainers image-spec to Dockerfile (#1502) 
This PR makes a few tiny changes to improve the overall quality of the docker image 🐳 . For reference more annotations can be found [here](https://github.com/opencontainers/image-spec/blob/main/annotations.md)
 2023-02-25 12:30:02 -08:00
Jonáš Kulhánek 079f419e54 Fixes bug introduced in #1499 preventing load_from_checkpoint to work correctly (#1501) 
* Call load_state_dict on model classes

* Fixing bug introduced in #1499
 2023-02-25 08:06:08 -08:00
Jonáš Kulhánek 93359b131e Call load_state_dict on model classes (#1499) 2023-02-25 08:00:04 +01:00
Jonáš Kulhánek 7e9af33c03 ns-process-data: fix image renaming for the --skip-colmap case (#1459) 
* Fix ns-process-data with skip colmap

* Fix docstring

* Fix pylint problem

* Change OrderedDict to dict
 2023-02-24 20:40:52 -08:00
Saurav Maheshkar a28442a82c chore: delete setup.cfg (#1495) 
Fixes #1489
 2023-02-24 11:18:58 -08:00
Ruilong Li(李瑞龙) 3933589b94 bump nerfacc to 0.3.5 (#1492) 2023-02-24 11:17:21 -08:00
Jingchen Ye e0ad53762e Rename train_split_percentage with train_split_fraction (#1497) 
rename train_split_percentage with train_split_fraction
 2023-02-24 11:16:37 -08:00