Commit Graph
1404 Commits
Author SHA1 Message Date
Matthew Tancik b375727f7e Update docstrings (#1165) 2022-12-23 14:20:48 -07:00
Matthew Tancik 4a27e5e929 Fix downscaling and type errors (#1164) 2022-12-23 14:07:07 -07:00
Alexander Kristoffersen fd33a1e950 PixelSampler refactor (#1163)
* moved collate methods as class methods, so sampling is only thing changed.

* disable pylint error, expected to be overrided.

* update.

* more pylint.

* final lint.

* cleanup, mask fix.
2022-12-23 00:49:28 -08:00
Matthias Blaicher 06642a5871 Support grayscale-only images in dataset (#1142)
* Support grayscale-only images in dataset

* lint
2022-12-22 11:16:03 -07:00
JamesPerlman 7fe4a77b96 fix typo: "dictioary" -> "dictionary" (#1162) 2022-12-22 11:00:47 -07:00
Matthew Tancik 335c5c3661 Fix dynamic batch logic during inference (#1160) 2022-12-21 22:50:05 -07:00
machenmusikandMatthew Tancik 8d4a82ef0b work around mismatch to allow rgb depth side-by-side output (#1156)
* use max resolution when not moving or training

* work around mismatch to allow rgb depth side-by-side output

* Update render.py

Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
2022-12-21 22:13:20 -05:00
machenmusik 0e1ea37308 when camera_type is equirectangular, add spherical metadata to rendered video (#1151)
* when camera_type is equirectangular, add spherical metadata to rendered video

* remove unnecessary CONSOLE.print

* refactor to make pylint happier

* get os.stat size properly; document camera_type argument

* write video on the fly to avoid holding all images in memory

Note: video render width and height were unspecified for spiral trajectory; this uses values for Nerfacto

* fix images output

* doc fix
2022-12-21 00:32:42 -05:00
Nicolas ZunhammerandNicolas Zunhammer 4a513825c4 [Fix] point cloud export broken in Dockerfile (#1148)
* Added Dockerfile to build docker image including all dependencies and nerfstudio, added description on how to user docker.

* Move docker description to Installation.md.

* Fix mask_filename indices after splitting train set.

* Rebase DOckerfile to newer image for updated libraries.

* Update docker container documentation.

Co-authored-by: Nicolas Zunhammer <n.zunhammer@tum.de>
2022-12-20 09:02:31 -08:00
Matthew Tancik af5953e2a8 v0.1.14 (#1145) v0.1.14 2022-12-18 13:15:28 -08:00
Martin Piala 09e1008069 Fix Discord link in the docs (#1143)
fix discord link
2022-12-18 10:48:49 -08:00
Matthew Tancik c338de4aa4 Support non-pinhole rendering (#1141) 2022-12-18 10:46:39 -08:00
Alexander Kristoffersen cc38d48294 Upgraded Gdown to fix data downloading. (#1140)
upgraded gdown to fix some data downloads.
2022-12-16 12:42:45 -08:00
Nikhil Mohan 29df594334 Minimal disk dataparser (#1128)
* wip

* merge upstream

* clkeanup

* cleanup

* cleanup

* cleanup

* more cleanup

* cleanup

* cleanup docs

* lint

* style fix
2022-12-16 20:16:20 +00:00
terrance dcee1087eb change position encoding to direction encoding for background color mlp 2022-12-16 19:54:39 +00:00
Ethan Weber 3bf490e845 adding data subset (#1135)
* adding nerfstudio-dataset

* removed file
2022-12-15 17:29:41 -08:00
Matthew Tancik 67cd746de3 Update Render View logic (#1134) 2022-12-15 16:14:13 -08:00
Matthew Tancik 3da0ca727d Update render ui to use leva (#1133) 2022-12-15 14:18:23 -08:00
Penn bc690632bb Use torch.where for faster contract (#1132)
use where for faster contract
2022-12-15 13:24:31 -08:00
terrance 7215766c51 Merge branch 'generative' of https://github.com/plenoptix/nerfactory into generative 2022-12-15 08:34:34 +00:00
terrance 4059cbaddb remove unused sampler, normalize predicted normals from network 2022-12-15 08:34:24 +00:00
Abhik Ahuja ahujaabhik@berkeley.edu 0080e60ba5 Tuning, more config changes 2022-12-15 06:15:24 +00:00
Matthew Tancik d51718ec2b Immediately update viewer when output or cmap changes (#1131)
* Immediately update viewer when output or cmap changes

* lint
2022-12-14 16:26:05 -08:00
Alexander Kristoffersen 5630148c50 Changed tinycudann to wheel to work with py3.8 (#1126)
Created using Colaboratory
2022-12-13 23:04:17 -08:00
Abhik Ahuja ahujaabhik@berkeley.edu 0fc4495348 Cleaned imports, more config options 2022-12-14 05:38:17 +00:00
Abhik Ahuja ahujaabhik@berkeley.edu cd93bc25fa Merge branch 'main' of github.com:nerfstudio-project/nerfstudio into generative 2022-12-14 05:07:21 +00:00
Abhik Ahuja ahujaabhik@berkeley.edu d826a7255e Location based prompting, density initialization fades, LR change 2022-12-14 04:22:15 +00:00
Matthew Tancik 6f85d7118f Add docs for KIRI Engine (#1124)
Add docs for KIRI engine
2022-12-13 18:37:31 -08:00
Abhik Ahuja ahujaabhik@berkeley.edu f1b3e6dd6b Shading hyperparameter tuning 2022-12-13 22:06:35 +00:00
Matthew Tancik a0a3def162 Fix datamanager dataparser_outputs (#1123)
* Fix datamanager dataparser_outputs

* Cast to float
2022-12-13 13:53:09 -08:00
Matthew Tancik c8daa1a1d7 Missing images error warning (#1122) 2022-12-13 13:24:22 -08:00
dozeri83anddror 96f269cc1a instant-ngp-bounded model (#1116)
* inerted a new model configuration instant-ngp-bounded

* added more remarks and small fixes

* went back to old near plane

* added the oprtion to get a file as well as directory in nerfstudio data parser

* pretify prev commit

* review fixes

* more clear explanation in README.md

* reverted readme changes

* fixed merge bug

* review changes. update config.data docs support for json files inputs

Co-authored-by: dror <you@example.com>
2022-12-13 13:05:48 -08:00
Matthew Tancik 21e0ec6cd8 Log start iter (#1119)
log start iter
2022-12-13 12:50:12 -08:00
Terrance Wang 008cc8f144 change normals grad calculation (#1108)
* change normals grad calculation

* changing normal calc
2022-12-13 12:39:41 -08:00
Tao 1a70665e76 Fix slow training issue when using mask (#1114) 2022-12-13 10:16:34 -08:00
Nikhil Mohan 98f13cbed4 Fix circular imports (#1115)
* wip

* remove bad changes

* update dmeo

* cleanup

* change name

* cleanup
2022-12-13 10:09:31 -08:00
Abhik Ahuja ahujaabhik@berkeley.edu 2525749974 Shading hyperparameter adjustements 2022-12-13 11:11:45 +00:00
Abhik Ahuja ahujaabhik@berkeley.edu 0dbebaf1cd Sigmoid on background, prompt in config 2022-12-13 06:29:52 +00:00
mcallisterdavid dd2a50574a Normals prediction training fixed 2022-12-13 04:55:56 +00:00
mcallisterdavid 64f7244feb Background MLP and SphereCollider 2022-12-12 23:51:06 +00:00
Alexander Kristoffersen 986f3a565d Colab working with Python3.8 (#1109)
changed away from the wheel, couldn't get it to work
2022-12-12 11:47:09 -08:00
Matthew Tancik 910e7bfb05 v0.1.13 (#1107) v0.1.13 2022-12-11 13:05:03 -08:00
Matthew Tancik 676f816156 Bump max res default (#1106) 2022-12-11 13:03:35 -08:00
Matthew Tancik b41ce8060a Save out dataparser transforms (#1105)
* Save out dataparser transforms

* Make missing folder
2022-12-11 13:02:50 -08:00
David McAllister 8671b63db8 Merge branch 'main' into generative 2022-12-10 13:44:01 -08:00
mcallisterdavid dda5bf9673 Dreamfusion pipeline 2022-12-08 06:50:36 +00:00
François Darmon 90447ab223 Bug correction auto_orient_and_center_poses (#1098)
When using auto_orient_and_center_poses with method="none" the returned pose if 4x4 (contrary to up and pca) which triggers an assertion error later. This modification solves it.
2022-12-07 09:40:53 -08:00
mcallisterdavid cbb50314b1 SDS loss added to dreamfusion 2022-12-06 07:54:23 +00:00
ksnzh e605b3344a Fix IndexError if ther is no mask filenames (#1095) 2022-12-05 22:10:55 -08:00
Matthew Tancik 006703bb64 Fix crash on camera delete (#1094) 2022-12-05 17:35:12 -08:00