tink/nerfstudio
4
0 Fork 0
mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-13 19:33:46 +08:00
Code Activity
1,765 Commits 85 Branches 40 Tags
e2e9a42c8d270a61ffd06404b817a2b9b384c18c
Commit Graph
1765 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Brent Yi e2e9a42c8d Merge branch 'main' into fix_gener_mesh_export 2023-11-30 18:36:17 -08:00
Brent Yi c96f5223b3 Update exporter.py 2023-11-30 18:36:09 -08:00
Panteleris PaschalisAdamRashid96Brent Yi
 		0cb410001b Fixes bug in PairPixelSampler when working with masked dataset (#2368) 
* Fixes bug in PairPixelSampler when working with masked dataset

* Formatting

* Black formatting now ok.

---------

Co-authored-by: AdamRashid96 <71362382+AdamRashid96@users.noreply.github.com>
Co-authored-by: Brent Yi <yibrenth@gmail.com>
 2023-12-01 01:11:11 +00:00
JoseandBrent Yi 49503c2175 Mps fix (#2436) 
* mps bugfix

* removed docs change

* Double quotes

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
 2023-12-01 00:04:01 +00:00
Brent Yi 4b673a9359 Merge branch 'main' into fix_gener_mesh_export 2023-11-30 16:02:08 -08:00
Jaggz H 43a7da36a5 Converted many @dataclass assignments for python 3.11 compatibility (#2630) 
Converted many @dataclass assignments to field()s for python 3.11 compatibility
 2023-11-30 23:51:36 +00:00
blacksino 747dd557f6 fix include_input for NeRFEncoding (#2642) 2023-11-30 23:07:26 +00:00
David Holtz 3d8af87290 Make nuScenes dataparser compatible with ParallelDataManager (#2635) 
The ParallelDataManager (see #2092) makes pytorch crash if the cameras instance's fx, fy, cx or cy tensors
are loaded from a common shared tensor.

This PR fixes the issue by cloning the respective tensors before passing them to the Cameras(...) constructor.
 2023-11-30 15:00:31 -08:00
Yosshi999Justin KerrBrent Yi
 		5a772b177d Bugfix: shape confusion in resizing (#2565) 
Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
Co-authored-by: Brent Yi <yibrenth@gmail.com>
 2023-11-30 05:57:43 +00:00
Justin KerrandBrent Yi 8b85c44b27 Patch spiral rendering w/ parallel datamanager (#2637) 
* fix jittering in markdown in viewer beta

* Revert "fix jittering in markdown in viewer beta"

This reverts commit 70ade42e46.

* print correctly formatted url in banner for viewer beta

* allow parallel datamanager in spiral rendering

* lint

* Update render.py

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
 2023-11-30 03:42:42 +00:00
Brent Yi c8c55521e8 Keyframe timing for beta viewer (#2638) 
* Add keyframe timing to beta viewer

* Nits

* New keyframe timing logic

* Bump viser version
 2023-11-30 00:52:37 +00:00
Chung Min KimandJustin Kerr 5865ecf323 Integrate scene click capability from original viewer (#2509) 
* Integrate scene click capability from original viewer

* filter non-click ScenePointerEvents from ClickEvent

* lint

* Put click origin+direction in nerfstudio world scale

* Update docs

* Update doc heading

---------

Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
 2023-11-29 14:48:58 -08:00
Jonáš Kulhánek 38726da219 Fix tangential camera distortion (p1,p2 in opencv camera) (#2627) 2023-11-29 19:48:41 +00:00
Chung Min Kim c896ee4e0a Remove PCA colormap bug for float output maps (#2620) 
Previously, "PCA" would be offered as a colormap option for float outputs (and throws "PCA is not a known colormap" error).
 2023-11-26 22:11:05 -08:00
Chung Min Kim 43703fa05a Bugfix; scrape pipeline for viewercontrol, not trainer (#2621) 
Scrape pipeline for viewercontrol, not trainer
 2023-11-26 21:56:49 -08:00
Rohan MathurandJustin Kerr 9528a3f717 Added UI to load camera path from existing path for the dataset (#2530) 
* added load camera path

* bugfixes

* fixed fov value in load camera path

---------

Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
 2023-11-16 04:09:48 +00:00
emma be37bcddea Remove an outdated comment in RayGenerator class (#2606) 
clean up comment
 2023-11-14 08:21:03 +00:00
Chris Heinrich b8736f704f Update LICENSE (#2597) 
Filling in the license to what I think it should be. We're adding this to our list of third party libraries
 2023-11-14 08:14:17 +00:00
Brent Yi 1f5f0c792b Make spherical harmonics test more forgiving (#2607) 2023-11-14 00:00:21 -08:00
AdamRashid96 5f5562b191 Render nearest training view (#2384) 
* render nearest camera to render view

* added lpips

* added the rotation distance and the depth check for the cameras

* render nearest training img

* formatting

* add flag for occlusions

* remove commented import

* remove comments

* fix pyright test

* remove None

* add assert

* fix pyright tests

* format

* made it a flag render-nearest-camera

* added default cams and dataset for tests

* maintain resolution of training images
 2023-11-13 10:23:05 -08:00
Yudong Jin f911fe7a0c Fix HTML render of README.md (#2599) 2023-11-11 08:05:06 -08:00
Gina Wu 1f6fb8337c Remove compile line in camera_utils (#2584) 
temporarily remove torch.compile in camera_utils
 2023-11-05 10:21:16 -08:00
Jonáš Kulhánek 85677d310f Fix torch.compile for torch 2.1 (#2577) 2023-11-02 09:28:11 +01:00
Justin KerrandBrent Yi 55616e1299 Print beta URL in banner correctly (#2569) 
---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
 2023-10-31 12:54:00 -07:00
Maxim BonnaerensandBrent Yi 793fca55e6 Make resetting the near_plane in NearFarCollider optional. (#2465) 
* Make resetting the near_plane in NearFarCollider optional.

It is not always desired to reset the near plane to 0.0 during inference.
Added an optional flag.

* no need to change precision

* Update scene_colliders.py

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
 2023-10-27 13:55:39 -07:00
Ethan Weber 87773bb081 Expose camera frustums size and occlusions to CLI (#2556) 
CLI expose for camera frustums
 2023-10-26 16:56:58 -07:00
フラハティ　仁 e4a0050d0d Add gradient scaling option to more methods (#2555) 
add gradient scaling to instant-ngp, mipnerf, tensorf, vanilla-nerf
 2023-10-26 15:15:58 -07:00
machenmusik 8a44e46179 ns-process-data images fix: multinerf uses equals sign (#2558) 
multinerf uses equals sign
 2023-10-25 16:08:16 -07:00
Cyrus Vachha dff216d4b8 Few viewer changes (#2553) 
* Viewer changes for render panel for fps and resolution

Small changes for the new viewer including changing the FPS slider to a text entry and fixing the incorrect resolution text box description.

* Check if render_time is nonzero in render state machine

Added a check if render_time is non zero in the render_state_machine file in the new viewer due to a divide by zero error occasionally causing the viewer to stop running. I noticed this usually happened when using nerfacto-huge.
 2023-10-23 01:05:19 -07:00
machenmusik e8cee3fdad make refine intrinsics during ns-process-data optional (#2550) 
ns-process-data will still refine intrinsics by default for compatibility.

Specify --no-refine-intrinsics to turn off.
 2023-10-20 21:08:51 -07:00
Daniel CrispellandBrent Yi f362eae608 Move only per-chunk data to the GPU to support rendering large images (#2481) 
* Move only per-chunk data to the GPU to support large images

* make type checking happy

* Use isinstance check

torch.is_tensor() doesn't have a TypeGuard annotation

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
 2023-10-20 19:41:19 -07:00
Justin Kerr bf32fc1e69 static imgs never rendered in multiclient (#2551) 
* fix jittering in markdown in viewer beta

* Revert "fix jittering in markdown in viewer beta"

This reverts commit 70ade42e46.

* static rendering never triggered
 2023-10-20 21:45:54 +00:00
Tobit Flatscher 23cc960bfc Fix pixel-perfect-sfm installation in Dockerfile (#2549) 
fix: Fix pixel-perfect-sfm installation in Dockerfile
 2023-10-20 18:42:42 +00:00
YangXiuyu 9e7144620b Missing a space in base_datamanager.py (#2546) 
Update base_datamanager.py
 2023-10-20 08:07:12 -07:00
Shiva Gantha e206079370 minor typing error (#2545) 2023-10-19 21:58:27 -07:00
Yueh-Cheng Liu 劉岳承andMatthew Tancik f31f3bba12 Add scannetpp dataparser (#2498) 
* Add scannetpp dataparser

* Fix formatting

* Remove unused import

* Add links and descriptions

* Update input file structure and remove unused code

* Reformat with black

---------

Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
 2023-10-19 18:19:11 +00:00
Gina WuJustin KerrBrent Yi
 		968176edb8 Support multiclient in viewer_beta with separate render threads for each client (#2519) 
* Initial multiclient, jittery screen bc fighting between clients

* Fix multiclient jitter with separate render threads for each client

* Handle client disconnect

* Fix viewer.init_scene and viewer_elements.get_camera for multiclient

---------

Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
Co-authored-by: Brent Yi <yibrenth@gmail.com>
 2023-10-19 10:25:44 -07:00
Ahmed Shariff 3dd162aae8 Fix pillow version to avoid error with ANTIALIAS (Fix #2378) (#2446) 
* Fix pillow version to avoid error with ANTIALIAS (Fix #2378)

* Revert pillow version, use fix for pillow ANTIALIAS from upstream
 2023-10-17 03:05:53 +00:00
SeaOtocinclus 6cbe070949 Update data_conventions.md (#2534) 
Fix typo in `distortion` word
 2023-10-16 23:11:43 +00:00
Brent Yi 042c7d1465 Bump tyro to 0.5.7 (#2393) 
* Bump `tyro`

* tyro 0.5.7
 2023-10-16 06:26:42 +00:00
Ji Shi ce06935f3d Fix datamanagers' get_rays_per_batch functions in case of using DynamicBatchPipeline (#2522) 2023-10-15 23:05:22 -07:00
Cyrus VachhaandBrent Yi 8e58021a47 Add camera_type dropdown in new viewer (#2525) 
* Add camera_type dropdown in new viewer

Added a gui dropdown menu for selecting the camera type. Currently, the render view doesn't update to preview the equirectangular or fisheye render.

* Updating the image url of nerfstudio logo images for the viewer

Changing the image urls to restore the nerfstudio logo in the viewer

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
 2023-10-14 21:46:53 -07:00
Cyrus Vachha e9a3bae859 Update URLs for readme and image references (#2527) 
* Update URLs for readme and image references

Update the image URLs and documentation links due to change in docs url structure. Files edited include readme, documentation, and legacy viewer files.

* Updating url in custom dataset
 2023-10-13 22:23:20 -07:00
Brent Yi d3934737a1 Upgrade pyright (#2526) 
* Upgrade pyright

* Resolve pyright errors

* Suppress trimesh error

* Run ruff
 2023-10-14 13:00:17 +08:00
Piero Toffanin 42cabedc60 Add ODM data processor (#2517) 
* Add ODM data processor

* Fix ruff warnings

* Re-format with black

* Add annotations

* Add explicit dtype

* Add explicit dtype

* Revert "Add explicit dtype"

This reverts commit 6f3cde1671.
 2023-10-12 20:08:45 -07:00
Justin Kerr 8e2a0651d0 Fix jitter viewer (#2505) 2023-10-10 17:49:52 -07:00
Justin Kerr dba20fcb26 minor patch for exporting pcs and meshes with parallel datamanager (#2503) 
* minor patch for exporting pcs and meshes with parallel datamanager

* format
 2023-10-10 17:18:16 -07:00
Justin Kerr e694f341a7 Move camera optimization out of datamanager and parallelize dataloading (#2092) 2023-10-10 14:52:25 -07:00
Justin Kerr 1b85fb528b patch for mkdirs on camera path json filepath (#2502) 
fix camera path json mkdir in viewer beta
 2023-10-10 13:09:09 -07:00
Jami PekkanenandMatthew Tancik 81db1808a7 Add documentation about unknown depth pixel convention (#2490) 
Updated the documentation to explicate that zero value in depth images is treated as unknown depth. This behavior is defined in https://github.com/nerfstudio-project/nerfstudio/blob/a484d255b4f71c55915afcfc52d90ec88963779f/nerfstudio/model_components/losses.py#L242

Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
 2023-10-08 21:26:10 -07:00