tink/nerfstudio
4
0
Fork 0
mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-11 02:24:38 +08:00
Code
1,282 Commits 85 Branches 40 Tags 295 MiB
ceda935e64
Commit Graph

1282 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Matthew Tancik
ceda935e64
Fix depth nerfacto exporting (#1453) 2023-02-19 13:53:01 -08:00
Matthew Tancik
73f0f5a16a
Fix mesh export normals (#1452) 
* Fix mesh export normals

* lint
 2023-02-19 13:43:43 -08:00
Nicolas Zunhammer
2901e5f31a
Bump Dockerfile versions, add user to sudoers list. (#1448) 
* Update Dockerfile, bump CUDA from 11.7.1 to 11.8.0, bump Colmap from 3.7 to 3.8, add user to sudoers list.

* Improve description.

* Fix wrong description and typos.

* Add better description.

* Fix build error of Dockerfile.

* Bump pytorch versions.

---------

Co-authored-by: Nicolas Zunhammer <n.zunhammer@tum.de>
 2023-02-19 13:58:33 +01:00
Matthew Tancik
df0f3205f4
Add ns-viewer docs (#1450) 2023-02-18 19:03:46 -08:00
Matthew Tancik
15dfc68453
Delete nerfstudio/.vscode directory 
Added by mistake.
 2023-02-18 17:13:46 -08:00
Sacha Lewin
8e4ae6bebf
Allow use of black or white background in Nerfacto models (#1441) 
* Allow black/white background color in Nerfacto

* Use white background in Nerfacto Blender Benchmark

* Fixed unused import

* Updated index for license headers script
 2023-02-17 20:39:10 -08:00
Matthew Tancik
2357332e66
Proposal network initial sampler (#1435) 
Allow first proposal sampling method
 2023-02-15 15:35:08 -08:00
Pablo Vela
6619dd1ac2
add monosdf normal loss and midas scale invariant depth loss (#1410) 
* add monosdf normal loss and midas scale invariant depth loss

* add context to scale/shift calc and normal loss, consolidate MidasMSE loss

* consolidated, add info on gradient reg term

* add info on ssi

* more documentation and type annotation

* move compute scale/shift to class

* fix pylint errors

* fix tensortype error

* fix comments

* change single var name and update comment

* fix input tensortype

* fix black error

* fix mask shape
 2023-02-15 13:49:35 -06:00
Matthew Tancik
be5274db09
Add arxiv link (#1434) 2023-02-15 10:05:18 -08:00
Jonáš Kulhánek
97498e3223
Improve ns-install-cli (#1396) 
* Improve ns-install-cli

* Remove unused code

* ns-install-cli conda specify encoding explicitly

* Fix missing directory in ns-install-cli

* Implement ns-install-cli deactivate for conda env

* ns-install-cli: conda create deactivate.d
 2023-02-15 17:46:55 +01:00
Pablo Vela
78eeb3bfe8
devcontainer for VSCode development (#1428) 
add devcontainer for easy development in VSCode
 2023-02-14 18:57:55 -06:00
NCJ
2878aff1c5
Fix LPIPS data range (#1425) 2023-02-14 10:18:33 -08:00
Matthew Tancik
71fd9f7245
Update SDS loss (#1426) 2023-02-14 10:14:48 -08:00
machenmusik
9c5423f181
Update to allow pytorch (and functorch) 1.13.1 (#1390) 
* Update pytorch (and functorch) to 1.13.1

Note that for existing installations, the following is recommended due to complications with older versions of functorch:
- `pip uninstall torch torchvision functorch`
- install the correct pytorch 1.13.1 version for your CUDA installation from https://pytorch.org/get-started/locally/ but add functorch to the command -- for example, Windows CUDA 11.7 would be `pip3 install torch torchvision functorch--extra-index-url https://download.pytorch.org/whl/cu117`
- reinstall nerfstudio e.g. `pip install -e .` from the source directory

* Update installation.md

* Allow 1.13.1, don't force

* pytorch 1.12.1 and 1.13.1

* Update README.md

* Update installation.md
 2023-02-14 08:59:26 -05:00
Matthew Tancik
9808ebbcb8
v0.1.17 (#1409) 2023-02-12 11:14:12 -08:00
Matthew Tancik
2b52f51b88
Downgrade nerfacc to 0.3.3 (#1408) 
reset nerfacc to 0.3.3
 2023-02-12 11:05:59 -08:00
Pablo Vela
a37c73fb07
sdfstudio dataparser/dataset (#1381) 
* add downloads for sdfstudio datasets

* add sdfstudio parser to work with sdfstudio data

* fix licensing and doc strings

* fix linter errors

* move depths/normals to metadata, create sdfdataset

* remove extra scenebox parameters

* more linting errors fix

* fix wrong annotation

* add in missing depth/normal files

* minor fixes

---------
 2023-02-12 10:31:31 -08:00
Matthew Tancik
71eacd5932
Update reality capture doc (#1404) 2023-02-11 10:51:22 -08:00
Mark Colley
259f3aa4dd
Fix IPython error display (#1397) 2023-02-10 15:30:57 -08:00
Matthew Tancik
3cf2bb09ac
Update citation (#1392) 2023-02-09 18:26:13 -08:00
Matthew Tancik
448e1072db
Update doc link 2023-02-09 17:55:51 -08:00
Jonáš Kulhánek
6368340aa2
Add ns-viewer command to run viewer only with model in eval mode (#1379) 
* Add ns-viewer command to run only viewer with model in eval mode

* Remove profiler and logger

* Fix ns-viewer

* ns-viewer remove writer.setup_local_writer

* ns-viewer add writer.setup_local_writer

* ns-viewer: update docs

* Delete outputs
 2023-02-09 17:31:16 -08:00
Jonáš Kulhánek
27b71325ff
Add support for is_fisheye flag in ingp transforms.json (#1385) 2023-02-09 17:23:33 -08:00
LSong
b653eef91c
add time (#1391) 
* add time

* fix black

---------

Co-authored-by: LcDog <12553253+LcDog@users.noreply.github.com>
 2023-02-09 16:43:21 -08:00
Matthew Tancik
df784e96e7
Colmap docs note (#1380) 2023-02-08 11:23:34 -08:00
NCJ
92cadf5ce4
Fix Multiple Typos (#1376) 
fix multiple typos
 2023-02-08 10:33:23 -08:00
Yiming Zhou
8c9c2ba2ab
Add support for sparse depth maps (#1373) 
Add support for sparse depth maps (#2)

* sparse depth maps

* pr comments

* unified loss

* minor

* lint
 2023-02-07 16:26:05 -08:00
Jonáš Kulhánek
2ff1d3b19e
Improve ns-process-data images when using existing COLMAP model (#1371) 
* Allow skipping copy+downscale of images in ns-process-data, fix bug when using --skip-colmap on images.bin with non-standard image names

* Rename flags and improve error messages

---------

Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
 2023-02-07 13:08:14 -08:00
Jonáš Kulhánek
6136745d75
Fix ns-train help (#1370) 2023-02-07 09:49:09 -08:00
Matthew Tancik
e749fbcf78
Trace Stable Diffusion (#1362) 
* Trace Stable Diffusion

* pylint

Co-authored by Terrance Wang
 2023-02-06 18:33:59 -08:00
Jonáš Kulhánek
59f71eda0e
Allow methods configs to be discovered from external packages. (#1357) 
* Allow method_config to be registered from external packages

* Add license

* Add MethodSpecification class + fix linter errors

---------
 2023-02-06 13:25:33 -08:00
machenmusik
bf64769128
add viewer.local config property when viewing local instance (#1358) 
If running local server instance, avoid using relays to communicate with the viewer.
 2023-02-06 15:53:27 -05:00
Francisca T. Gil Ureta
2ffe4f9036
Handle uncalibrated Metashape sensor (#1359) 
This fix allows loading Metashape XML files which
contain an additional uncalibrated sensor.

Metashape XML format keeps unmatched images but
assignes a dummy sensor to them. The sensor has
no calibration data.

Co-authored-by: gilureta <gilureta@amazon.com>
 2023-02-06 10:22:19 -08:00
ManuConcepBrito
cddf6a6569
Consistent naming for depth maps in Polycam (#1352) 2023-02-05 11:04:53 -08:00
Matthew Tancik
9f5da51319
Improve viewer colormap choices (#1348) 2023-02-03 23:15:05 -08:00
machenmusik
fad5a839aa
double-quote filenames in process-data commands so that on Windows, paths with spaces don't fail (#1347) 
* double-quote filenames in commands so that on Windows, paths with spaces don't fail

* reformatting by black
 2023-02-03 21:01:37 -05:00
machenmusik
319a2b965c
New config parameter --viewer.codec defaults to VP8, but allows H264 (#1343) 
* New config parameter --viewer.codec defaults to H264 rather than VP8

* make quantize clearer

* change codec to Literal

default is VP8 due to libx264 log spam, see https://github.com/nerfstudio-project/nerfstudio/pull/1343#issuecomment-1416235500

* isort

* pylint, including python 3.7 compatibility
 2023-02-03 13:38:40 -08:00
Matthew Tancik
59d7e99c80
Create shaders (#1344) 2023-02-03 11:21:54 -08:00
Jeffrey Hu
a0976d1ff8
Fix depth-supervised nerf when using z-buffer depth. (#1340) 
* fix z buffer depth

* remove script
 2023-02-02 18:22:55 -08:00
Matthew Tancik
2e79c93cd2
Fix normals visualization (#1341) 2023-02-02 18:06:11 -08:00
Terrance Wang
cf1794acb1
Add lambertian renderer (#1336) 
* add lambertian shading renderer

* adding more functionality

* adding to comments

* optionally detach normals, fixing naming and typing

* Update description

---------

Co-authored-by: Matt Tancik <mattt4001@gmail.com>
Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
 2023-02-02 13:07:14 -08:00
Matthew Tancik
3ab9352be8
Set min render value for viewer (#1339) 2023-02-02 12:55:03 -08:00
Matthew Tancik
ef9e00e614
Check if curl is installed (#1337) 
* check if curl is installed

* lint
 2023-02-02 10:11:41 -08:00
hturki
d547279a92
add option to log training gradients (#1334) 2023-02-02 09:48:45 -08:00
Matthew Tancik
3a416a387b
Dont move viewer outputs to cpu (#1335) 2023-02-01 17:33:06 -08:00
Matthew Tancik
db83068fcd
Update optimizer docstrings (#1333) 2023-02-01 15:15:08 -08:00
hturki
48ec36e53f
Add support for gradient clipping (#1331) 
implement optional gradient clipping
 2023-02-01 14:55:07 -08:00
Matthew Tancik
53a830a691
Safe normalize (#1332) 2023-02-01 13:22:32 -08:00
Matthew Tancik
e979f89200
Avoid protobuf 3.20.0 (#1330) 2023-02-01 12:21:57 -08:00
Matthew Tancik
567268854b
Cleanup aabb intersection logic (#1329) 2023-02-01 12:18:09 -08:00