tink/nerfstudio
4
0 Fork 0
mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-15 04:13:57 +08:00
Code Activity
1,323 Commits 85 Branches 40 Tags
fd5b8be160c199e6f47a3d981d16085fc678b165
Commit Graph
41 Commits
Author SHA1 Message Date
Matt Tancik 390b910339 Cleanup 2023-02-02 16:59:07 -08:00
terrance 9e4bc773ad turn grad accum off by default, decrease background mlp size, add overhead text embedding 2023-02-02 23:24:46 +00:00
Matt Tancik ae8a2f23c1 Merge remote-tracking branch 'origin/main' into generative 2023-02-01 14:40:15 -08:00
LSongandmachenmusik e73692e599 nerfplayer with ngp and nerfacto (#1277) 
* nerfplayer with ngp and nerfacto

* update comments

* update cpp extension build

* avoid Windows repeated CUDA compile

---------

Co-authored-by: machenmusik <machenmusik@users.noreply.github.com>
 2023-01-31 11:56:28 -08:00
terrance 3611381d8d merging 2023-01-23 15:44:09 +00:00
matsurenandMatthew Tancik 408ab709ec Fix typo (#1231) 
* Fix typo COLAMP->COLMAP

* Fix more typo

Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
 2023-01-16 12:12:55 -08:00
terrance 68e8d3e9ce merging 2023-01-16 18:43:59 +00:00
terrance 49bbd5405d merging 2023-01-16 18:43:24 +00:00
Dreek Fire 5710b09b6d Add hashmap size and num_levels to instant_ngp_field, issue 1158 (#1196) 
add hashmap size and num_levels to instant_ngp_field, issue 1158
 2022-12-31 23:30:27 -08:00
jake-austin 22340b37f3 Updating dreamfusion to use custom trainer, fixed bug, multi-gpu support (put diffusion on one specific device), merged with main 2022-12-28 07:06:15 +00:00
jake-austin 36258b62c1 Merge branch 'main' into generative 2022-12-28 04:35:58 +00:00
Matthew Tancik b375727f7e Update docstrings (#1165) 2022-12-23 14:20:48 -07:00
terrance dcee1087eb change position encoding to direction encoding for background color mlp 2022-12-16 19:54:39 +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 cd93bc25fa Merge branch 'main' of github.com:nerfstudio-project/nerfstudio into generative 2022-12-14 05:07:21 +00:00
Terrance Wang 008cc8f144 change normals grad calculation (#1108) 
* change normals grad calculation

* changing normal calc
 2022-12-13 12:39:41 -08:00
Abhik Ahuja ahujaabhik@berkeley.edu 0dbebaf1cd Sigmoid on background, prompt in config 2022-12-13 06:29:52 +00:00
mcallisterdavid 64f7244feb Background MLP and SphereCollider 2022-12-12 23:51:06 +00:00
Matthew Tancik 676f816156 Bump max res default (#1106) 2022-12-11 13:03:35 -08:00
Abhik Ahuja d2e08ed1bc Train normals in Dreamfusion 2022-11-28 20:01:12 -08:00
Abhik Ahuja 44d6431c43 Normals in dreamfusion 2022-11-28 14:49:46 -08:00
Abhik Ahuja b57781ab0c Added dreamfusion to CLI, removed direction embeddings 2022-11-28 14:21:00 -08:00
David McAllister 8f36e25510 Merge branch 'main' into generative 2022-11-28 12:57:39 -08:00
Zak Murezandzmurez a7df91edc8 config nerfacto (#1020) 
Co-authored-by: zmurez <zmurez@eng.ucsd.edu>
 2022-11-27 15:56:06 -08:00
Abhik Ahuja 303d16c659 Removed view direction from RGB to calculate albedo 2022-11-23 23:08:14 -08:00
terrance 6f4aad451e starting the framework for dreamfusion 2022-11-23 08:43:57 +00:00
Julian Knodt 0d3cfe2d38 bugfix: AABB normalized_positions to [-1, 1] (#998) 
AABB normalized_positions to [-1, 1]

Previously, SceneBox.get_normalized_positions() returned a value in 0,1.
This was fine for InstantNGP and Nerfacto, which use these values directly in an MLP.
For TensoRF though, this was an error because grid sample expects values in the range [-1,1].
Thus, I think only 1/4th of the encoding planes were actually being used, and half of the
encoding lines were.
 2022-11-21 12:15:01 -08:00
Ethan WeberMatthew Tancikterrance
 		b829499c12 Computing and predicting normals (#905) 
* staring normals PR

* code runs but visualization looks bad

* Camera and world coordinate conventions (#889)

* documented coordinate conventions without a figure for now

* another sentence

* update frames docs

* explain intrinsics and extrinsics

* more comments

* fix build

* Start viewer with more accurate speed calculation (#899)

Start viewer with more accurate speed calc

* Minor doc updates (#903)

* fix conflicts

* code runs but visualization looks bad

* normals implemented and vis fixed. still debugging quality

* minor name change

* comment

* fix black

* lint

* predicting normals

* adding detach

* predicted normals

* improved normals prediction performance

* cleaning code

* cleaning code

* cleaning code

* adding type to function param

* fixing tensorf forward func

* reverting tensorf changes

* fix style with tensorf field

* adding normals check to tensorffield

Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
Co-authored-by: terrance <terrance.3512@gmail.com>
 2022-11-20 13:22:37 -08:00
Matthew Tancik 4b65180a57 Add missing activation (#933) 2022-11-10 13:27:10 -08:00
Nikhil Mohan 1a24f3e58c Refactor Data Pipeline (#896) 
* add none check

* black formatting

* cleanup

* cleanup

* fix tests

* remove new line

* init

* toy example working

* semantic nerf working

* simplify pixel samplers

* cleanup + fix tests

* comments

* fix tests

* fix tests
 2022-11-06 07:40:43 -08:00
Terrance WangandMatthew Tancik 7106f42fcc tensorf (#586) 
* tensorf wip

* model changes

* tuning model

* changing imports

* merging

* changing rff encoding to nerfencoding, basis matrix should be properly updated, changed density activation, lr scheduler

* debugging tensorf

* debugging tensorf

* tensorf debugging

* tensorf debugging

* tensorf debugging

* tensorf debug

* debugging tensorf, fixed bug with collider

* tuning model, ray sampling

* adding thresholding for ray computations

* removing unused imports

* making more params configurable in config, adding spherical harmonics

* removing scene contraction, adding arg docstrings

* fixing style

* Fixing bug

Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
 2022-11-02 14:32:03 -07:00
Justin Kerr a4755a1349 Sample proposal networks on a schedule to speed training (#770) 2022-10-13 20:14:21 -07:00
Ethan WeberakristoffersenJustin Kerr
 		2150bad0e4 Reducing flicker artifacts for nerfacto method (#750) 
* pose opt default nerfacto.

* added SO3 cam pose optimization which is slightly faster (~2.2m/iter) than BARF

* added occupancy grid with placeholder until nerfacc is updated to query density from it

* added occupancy grid sampling as the level 0 in proposal hierarchy, relies on nerfacc 0.1.7 (on pypi)

* merge main

* merge main

* minor changes to sampling

* adjusted sample number

* refactor occ grid stuff, settle on decent params

* nograd proposal sampling

* param tweaks

* varying resolution proposal networks

* params

* merged main

* optimizer update

* remove occ grid

* remove double nerfacto samples

* set single jitter to true

* remove pdb

* more changes

* fix method defaults

* fix pylint

* remove occupancy fn

Co-authored-by: akristoffersen <akristoffersen@berkeley.edu>
Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
 2022-10-11 14:21:00 -07:00
Matthew Tancik 6162f9d81f Tancik/remove valid mask (#655) 
* Install updates

* Remove valid mask logic
 2022-10-04 13:54:39 -07:00
Ethan Weber 05ba4b6b00 semantic nerfw (#640) 
transients not working right now
 2022-10-03 20:36:32 -07:00
evonneng 968959bdc9 quickstart updates + (other nits+links added to repo) (#633) 
* small changes

* rewrite quickstart + readme

* fixed all licensing headers

* nits
 2022-10-03 16:01:16 -07:00
Ethan Weber c20fed83bb moving around files (#616) 
moved around files
 2022-10-02 16:54:34 -07:00
Matthew Tancik afda888591 tcnn encoding integration (#608) 
* tcnn encoding integration

* Add tests, fix lint

* lin
 2022-10-02 10:33:43 -07:00
Matthew Tancik 4110bd7a3e Rename scene bounds (#605) 2022-10-01 20:41:36 -07:00
Ethan Weber e13d401b16 restructure codebase pre release (#602) 
* moving a lot

* building
 2022-10-01 16:36:25 -07:00
Matthew Tancik 1f83ad03db Rename to nerfstudio (#589) 2022-09-29 23:42:15 -07:00