4
0
mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-11 02:24:38 +08:00
Commit Graph

1708 Commits

Author SHA1 Message Date
Rohan Mathur
afcc8434d0
fixed link to viser to be functional link cause previous 404ed (#2486) 2023-10-03 09:20:58 +02:00
Maxim Bonnaerens
0d746b1363
Fourier Feature encodings and polyhedron encodings (#2463)
* Fourier Feature encodings and polyhedron encodings

Rework RFFEncoding to be a subclass of the more general Fourier Feature
Encodings and introduce Polyhedron encodings as introduced in
mipnerf360.

* b_matrix -> basis

* Add typing

* fighting pyright

* use scale argument

* continue the fight

* ignore

* ignore em all

* add docstring and rename generate_basis to generate_polyhedron_basis

* Try to please pyright with assert

* Immediately allocate tensor on correct device

* private functions and docstrings update

* doc fix continued

---------

Co-authored-by: Jonáš Kulhánek <jonas.kulhanek@live.com>
2023-10-02 21:07:34 +00:00
Reza Kermani
c2f5e68d54
fixing broken links in README (#2483)
fixing broken links
2023-10-02 05:31:02 +02:00
Jonáš Kulhánek
b78d0faa12
ns-render - render all images (#2459)
* ns-render - render all images

* Fix commonprefix->commonpath

* Fix raw rendering
2023-10-01 22:12:48 +02:00
pierremerriaux-leddartech
7856aa0060
fix:correction of PairPixelSampler in case of using masks with depth-nerfacto (#2477)
fix:correction of PairPixelSampler in case of using masks
2023-09-29 16:49:20 -07:00
Brent Yi
c93b374d08
Don't deploy docs from pull requests (#2482) 2023-09-29 12:33:19 -07:00
Matthew Tancik
bbe31736f3
Update README.md 2023-09-29 10:48:51 -07:00
Matthew Tancik
88d5b03a80
Remove rtd (#2478) 2023-09-28 18:15:35 -07:00
Ruilong Li(李瑞龙)
169030199e
Update doc.yml (#2479) 2023-09-28 18:14:40 -07:00
Gina Wu
593950efec
Update colmap installation instructions with conda (#2473) 2023-09-27 10:45:58 -07:00
Chung Min Kim
4cdeaa6eec
Track all viser GUI folders to avoid folder duplicates (viewer-beta) (#2466)
* Track all viser GUI folders to avoid folder duplicates

* lint

---------

Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
2023-09-25 13:14:51 -07:00
Jonáš Kulhánek
2864c52618
Fix COLMAP dataparser masks and depthmaps (#2467) 2023-09-25 08:37:08 -07:00
Maxim Bonnaerens
53037ba8a7
Allow custom sampler in ProposalNetworkSampler (#2464)
* Allow custom sampler in ProposalNetworkSampler

This allows custom (pdf)samplers in distinct repositories while still
using the base ProposalNetworkSampler.

* sampler should inherit from pdf sampler

* docstring
2023-09-24 12:06:16 +02:00
Ruilong Li(李瑞龙)
e0f0cd05aa
Migrate doc from RTD to gh-pages (#2460)
* gh-pages workflow

* update doc.yml

* update

* remove RTD

* change action to main

* test fail on warning

* fail on warnings

* get back .readthedocs.yml, a bit cleanup

* revert SHA of index.md file
2023-09-22 23:04:02 -07:00
Maxim Bonnaerens
8812d7a5b0
.vscode settings match move to ms-python.black-formatter (#2456)
Co-authored-by: Brent Yi <yibrenth@gmail.com>
2023-09-22 17:45:05 +00:00
Maxim Bonnaerens
52f26e82b3
Do not materialize mlp_head if no field_heads (#2457)
In case it is used in a proposal network we avoid initializing the head.

Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
2023-09-22 15:36:51 +00:00
フラハティ 仁
2fd8b59d20
Add background_color config to keep consistent with other models (#2455)
* add backgorund_color config

* removed unused color import
2023-09-22 07:40:20 -07:00
Matthew Tancik
c87ebe34ba
v0.3.4 (#2452) 2023-09-21 18:38:22 -07:00
Jonáš Kulhánek
76f8bcf953
Disable loading colmap points by default (#2451) 2023-09-21 13:51:35 -07:00
Justin Kerr
e0d8f04267
Render oriented crops in viewer beta (#2447)
* add obb to the rendering pipeline

* useless line

* lint

* remove todo

* pyright

* more pyright
2023-09-19 16:48:54 -07:00
Brent Yi
3e1d4af821
Add share link support for beta viewer (#2445)
* Add share link support for beta viewer

* More consistent CLI experience

* fix viewer jitter by adding atomic update on camera pose

* change to make_share_url

* fix

* remove incorrect assert

---------

Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
2023-09-19 16:22:55 -07:00
フラハティ 仁
b0e700137b
Allow the option for timestamp to be generated for ns-train --load-config (#2442)
* Fix timestamp for ns-train --load-config

* Remove whitespace
2023-09-18 21:13:48 -07:00
Jonáš Kulhánek
ef2fd3dbe1
Fix import error when tcnn installed but CUDA runtime not available (#2429) 2023-09-15 17:18:23 -04:00
Sid Mehta
7269a7ee16
Add Comet Logging (#2431)
* initial commit

* fixed naming

* added comet_ml as depedency

* added comet to docs

* Update custom_gui.md

* Update models.md

* Update benchmarking.md

* added Comet to ReadMe

* added decorator

* fixed link and added comet examples

* fixed link and added comet example

* fixed format

* fixed type ignore error

* fixed readme typo

* fixed typo
2023-09-15 09:21:09 -07:00
anc2001
805e6e702d
fix pixel sampling with masks issue when data is list (#2369)
Co-authored-by: Brent Yi <yibrenth@gmail.com>
2023-09-14 16:11:15 +00:00
Jonáš Kulhánek
e9330d515d
Colmap parser: fix downscale for complex paths (#2425) 2023-09-13 10:55:24 -07:00
Maxim Bonnaerens
cc98fb6bd4
Fix benchmarking: apply get_background_color in renderer and set profiler to none (#2397)
* apply get_background_color and set profiler to none

* Apply override first

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
2023-09-11 18:07:52 +00:00
Jonáš Kulhánek
570ccf3c0a
Rename COLMAP 3D point features (#2417) 2023-09-11 09:00:44 -07:00
Jonáš Kulhánek
ead9b37c65
Allow colmap parser to load 3D points (#2408) 2023-09-11 07:50:18 +00:00
Sebastiaan
77ac7d0cf8
Fix issue when extracting all frames from a video. (#2413)
* Remove superfluous num_frames

* process_data video: Always use -vsync vfr, even when extracting all images.
2023-09-08 16:00:10 -07:00
drewgilliam
06e59ed1ec
camera/plugin docs (#2412)
* api docs for cameras & plugins

* fix docstrings
2023-09-08 09:14:16 -07:00
Jonáš Kulhánek
6af0bcfbf8
Unify dataparser and method discovery (#2398)
* Unify external dataparser registration

* Unify dataparser and method discovery
2023-09-08 08:26:41 +00:00
Justin Kerr
85ef567682
Flesh out viewer beta (#2086)
* Increase max_res of first proposal network

* fix render statemachine logic for viewer beta

* clicking on cameras in the viewer

* fix fov calculation, update camera positions while training

* cleanup

* backup

* fix configure theme

* Fix theme configure for latest dev version of viser

* Fix runtime errors

* add set up direction button

* add pause resume button

* Export panel

* Render tab skeleton

* make responsiveness more snappy by stopping training

* depth composite

* start implementing viewercontrol in new viewer

* refactor background img to use depth and add depth layering option

* show/hide images

* speed up rendering

* fix crop color background

* crop

* rotated crops

* rotated crops

* transform handle on crop box

* fix xyzw for crop

* oriented crop export for pointclouds, not for meshes yet

* Initial render panel

* Fix export button

* Theme tweaks

* fix background issue in cropping

* export rotated poisson meshe

* double normals definition in export panel

* Visual nits

* remove tsdf from export panel

* Add licenses

* Fix some CI errors

* Type fixes

* Fix tests

* Fix numpy broken

* various bugfix

---------

Co-authored-by: Brent Yi <yibrenth@gmail.com>
Co-authored-by: terrancewang <terrance.3512@gmail.com>
2023-09-08 05:10:00 +00:00
Zhensheng Yuan
9625ab713c
Fix the problem that camera will be freezed when moving forward (#2404)
* fix camera freezed when moving forward

* simplify code

---------

Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
2023-09-08 00:31:02 +00:00
drewgilliam
d947f6e485
Update engine docs (#2405)
* build docs for nerfstudio.engine.trainer and nerfstudio.engine.callbacks

* docs minor edit for new_methods.md
2023-09-07 18:17:03 +00:00
drewgilliam
d947aee713
Specify path for test outputs (#2400)
* test_train - set_timestamp, output_dir in pytest tmp_path

* test_train typehints
2023-09-07 18:08:57 +00:00
drewgilliam
4d0033343c
NERFSTUDIO_METHOD_CONFIGS callable MethodSpecification (#2385)
* NERFSTUDIO_METHOD_CONFIGS allow method specification as callabale (function or class)

* docs - NERFSTUDIO_METHOD_CONFIGS accepts function or derived class
2023-09-05 13:55:08 -07:00
Panteleris Paschalis
a121d76fd0
Fixes ARG before FROM bug (#2371)
Fixes ARGS before FROM bug
2023-08-31 22:04:01 +00:00
Maxim Bonnaerens
242c23f0f0
cast background to device (#2381)
* cast background_color to device

* make onliner instead
2023-08-29 15:07:43 -07:00
Justin Kerr
d56338bce1
Fixes crop background color override (#2373)
fix crop color background
2023-08-27 11:50:57 -07:00
elenacliu
ae5d569376
Fix: typo in PairPixelSamplerConfig's description (#2372)
Co-authored-by: AdamRashid96 <71362382+AdamRashid96@users.noreply.github.com>
2023-08-26 03:09:44 -07:00
Sasha Sax
6e37b2b542
Enable SparseNerf depth ranking loss to be used with GT/Sensor depth (#2312)
* add ranking loss to depth-nerfacto with GT depth

* formating

* pair pixel sampler bug fix from pr #2315

---------

Co-authored-by: Sasha Sax <asax@stanford.edu>
Co-authored-by: Ethan Weber <ethanweber@berkeley.edu>
Co-authored-by: AdamRashid96 <abrashid@berkeley.edu>
Co-authored-by: AdamRashid96 <71362382+AdamRashid96@users.noreply.github.com>
2023-08-26 02:56:52 -07:00
Mocax
aaa6c3aa1d
Fix the starting command of docker. (#2357)
To prevent abusing of root privilege, please use custom user privilege to start.

If not, sometimes the Docker images may be started with the permissions of root or other users. If you modify the mounted files in the container , it will cause permission errors or other errors.

Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
2023-08-25 01:08:56 +00:00
Zhan Xu
ebceb52f55
save sfm depth as png to keep 16bit. save depth_file_path as relative… (#2317)
save sfm depth as png to keep 16bit. save depth_file_path as relative path

Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
2023-08-24 22:30:26 +00:00
Rohan Mathur
48135ee4c8
Added a pytorch implementation of OmniCV's to remove equilib package usage (#2350)
* added pytorch omnicv implementation in order to not use GPL equi2pers

* renamed rotation matrix function to decrease confusion

* fixed docstrings

* fixed linting

* removed pyequilib from dependencies
2023-08-20 21:34:18 -07:00
Ethan Weber
9315cad5f5
Switching Nerfstudio Dataset data to GDrive URLs (#2358)
* switch urls to gdrive

* added comment with explicit link to gdrive url
2023-08-19 13:48:28 -07:00
James Gardner
cba8d22d3b
Optimizers.scheduler_step() bug fix (#2352)
optimizer bug fix
2023-08-18 09:01:50 -07:00
Ethan Weber
1b430590c8
Nerfstudio Feedback Form (#2351)
* nerfstudio feedback form with a url placeholder

* text change

* updating feedback form url

* adding another url
2023-08-17 20:40:53 -07:00
Matthew Tancik
61548ceba1
v0.3.3 (#2349) 2023-08-17 11:59:04 -07:00
Sasha Sax
9cd957f776
Update pixel_samplers.py (#2327)
* Update pixel_samplers.py

Now uses the specified batch_size param in sample_method()

* black

---------

Co-authored-by: Matthew Tancik <matt@lumalabs.ai>
2023-08-17 18:04:51 +00:00