Commit Graph
270 Commits
Author SHA1 Message Date
Matthew Tancik 4e6c52c8fd Update sphinx docs (#1695) 2023-04-04 11:08:09 -07:00
James Gardner 9a01738b0e Adding NeRF-OSR Dataset (#1626)
* Added NeRFOSR Dataparser

* updating nerfosr dataparser

* fix import order in datamanager

* updating nerfosr dataparser

* update nerfosr dataparser
2023-03-17 15:53:19 -07:00
Rohan MathurandMatthew Tancik ea9a066f8f Removed deprecated insta360 (#1621)
* removed insta360 and also updated equirect images docs to include cropping

* removed unused import

---------

Co-authored-by: Matthew Tancik <tancik@berkeley.edu>
2023-03-17 12:54:45 -07:00
ksnzh 505ebe6793 fix missing param refine-pixsfm (#1618) 2023-03-17 11:52:57 -07:00
Rohan Mathur 2838cfc8a5 Adding the crop code made for videos to images (#1598)
* added equirect support

* added cropping for planar image input

* random comment

* bug fix and running command

* added crop-factor to docstrings
2023-03-14 12:04:28 -07:00
Pablo Vela 630babacd6 Add option to use Pixel Perfect SFM (#1554)
add pixsfm option when using hloc
2023-03-12 16:32:33 -04:00
Frédéric DevernayandFrédéric Devernay 21a452f1b4 scripts/exporter.py: export PLY compatible with PCL (#1572)
* scripts/exporter.py: export PLY compatible with PCL

Use the newer Open3D Tensor API to write pointclouds as float32, which
are compatible with PCL (see https://github.com/isl-org/Open3D/issues/1633).

fixes https://github.com/nerfstudio-project/nerfstudio/issues/1571

* exporter.py: pylint: disable=no-member

fixes https://github.com/nerfstudio-project/nerfstudio/actions/runs/4377569585/jobs/7661246358#step:10:13

open3d.core.Dtype has been around since open3d 0.11.0 http://www.open3d.org/docs/0.11.0/python_api/open3d.core.Dtype.html

---------

Co-authored-by: Frédéric Devernay <f-dy@users.noreply.github.com>
2023-03-10 10:20:36 -08:00
Rohan Mathur 403ab26f0c Changed percent-crop to crop-factor so it's less confusing (#1575)
* changed percent-crop arg to crop-factor so it's more clear that it's a float

* added error if crop values are less than 0 or more than 1

* added value hint and changed error to console thing

* added imports

* fixed linter issues

* refixed linter issues
2023-03-09 12:23:50 -08:00
Rohan Mathur 982e527bee Added video cropping for equirectangular and made it independent of mask in normal videos (#1542)
* started bottom crop functionality

* first draft of cropping

* cleaned up and debugged cropping equirectangular and re added mask stuff just without percent crop

* added nonequirectangular video crop

* added left right crop for equirectangular

* shortened equirect utils

* finished regular video cropping

* removed print, added underscores, changed type to List[float]
2023-03-02 18:24:59 -08:00
Matthew Tancik bfaf11cd72 Remove dataparser dependency (#1529) 2023-02-27 18:32:40 -08:00
Georgy Ponimatkin 4a9764d3c4 Fixing data processing script when depth is not used (#1527)
Update process_data.py

Fix image_id_to_depth_path = {} to image_id_to_depth_path = None
2023-02-27 18:23:58 -08:00
Jonáš Kulhánek 7309273d92 Add support for more colmap camera models in ns-process-data (#1500)
* Add support for more colmap camera models in ns-process-data

* Fix bugs introduced in #1457
2023-02-26 18:53:08 +01:00
Georgy Ponimatkin 7da588c5d2 Extending ns-render to support loop rendering using interpolated cameras (#1508)
* Extending ns-render to support loop rendering using interpolated cameras.

* Adding docstring for render.py. Applying formating.

* Expanding docstrings for class. Renaming trajectory type.

* Removing mentions of loop from render.py.
2023-02-26 09:30:19 -08:00
Paul Wais 5c73766653 SFM: sfm-based depth, some breadcrumbs for pycolmap (#1457)
* save

* save

* more cleanup

* save

* save

* update phototourism

* save

* works

* works

* cleanup

* cleanup

* lint

* python3 default

* cleanup
2023-02-25 21:10:53 -08:00
Jingchen Ye 871eb0f7d3 Rename friends dataset to sitcoms3d (#1503)
* Rename friends dataset with official name sitcoms3d

* Rename downloaded folder

* Fix pylint
2023-02-25 14:38:23 -08:00
Ruilong Li(李瑞龙) 7dc7129cf8 fixes for nerf synthetic dataset (#1507)
* fixes for nerf synthetic dataset

* restore eval script

* fix format with black
2023-02-25 14:37:10 -08:00
Jonáš Kulhánek 7e9af33c03 ns-process-data: fix image renaming for the --skip-colmap case (#1459)
* Fix ns-process-data with skip colmap

* Fix docstring

* Fix pylint problem

* Change OrderedDict to dict
2023-02-24 20:40:52 -08:00
Sacha Lewin 151b1060fe Uniform Sampler in Nerfacto (#1464)
* Allow black/white background color in Nerfacto

* Use white background in Nerfacto Blender Benchmark

* Fixed unused import

* Updated index for license headers script

* Removed debug code in NGP models

* Uniform initial sampler config in Nerfacto

* Undo changes in settings.json

* Removed unwanted settings file

* Removed unneeded config parameter

* Use uniform sampler on Blender benchmark
2023-02-21 09:17:57 -08:00
796fad8bcb Equirectangular input (#1446)
* started adding equirectangular to process_data

* was multiplying frame by 255 twice

* added equi2planar configs for the 3 presets

* fixed presets

* setup process data

* changed variable name and comment

* fixed middle preset

* removed third preset

* added progress bar and fixed video for equirectangular input

* fixed whitespace stuff

* added pyequilib dependencey

* Updated for JPG support for equirectangular image input

Updated process_data_utils for JPG support for equirectangular image input, since even though .jpg images worked, .JPG images (output from 360 camera software) were not working.

* changed file type matching

* added equirect utils

* added license header

* added docstring on equirect utils

* added heuristic for image size

* added heuristic for videos

* fixed linty stuff

* shortened code

* raised error if no ims in directory

* Updated ProcessVideo for fixing directories for equirectangular input

Updated the ProcessVideo for equirectangular input to make the image directory have the correct perspective projections. The original equirectangular images are copied into a temp_images folder which also holds the perspective projections. This folder is deleted once the perspective projections are copied into the process data images folder.

---------

Co-authored-by: cvachha <cyrus.vachha@yahoo.com>
Co-authored-by: cvachha <cvachha549@gmail.com>
2023-02-20 10:58:42 -08:00
Matthew TancikandDavid McAllister 36514797fd Support multiple versions of stable diffusion (#1461)
Co-authored-by: David McAllister <davidrmc2@gmail.com>
2023-02-20 10:12:41 -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
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 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
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
NCJ 92cadf5ce4 Fix Multiple Typos (#1376)
fix multiple typos
2023-02-08 10:33:23 -08:00
Jonáš KulhánekandMatthew Tancik 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
Matthew Tancik e749fbcf78 Trace Stable Diffusion (#1362)
* Trace Stable Diffusion

* pylint

Co-authored by Terrance Wang
2023-02-06 18:33:59 -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
Matthew Tancik ef9e00e614 Check if curl is installed (#1337)
* check if curl is installed

* lint
2023-02-02 10:11:41 -08:00
MaroonAmor 91d61162b7 Corrected the order of texture arguments (#1300)
corrected the order of texture arguments
2023-01-29 09:22:10 -08:00
Matthew Tancik b5031dd814 Enable rendering with crop (#1295) 2023-01-26 14:22:43 -08:00
cvachha 2e843eb2df Updated Blender add-on for calculating duration (#1288)
Updated Blender on calculating duration

Updated how the Blender add on calculates duration with frame steps and added the case when frame step size is 0.
2023-01-25 18:05:31 -08:00
ManuConcepBrito 828d6bc893 Depth data loading for Polycam LiDAR data (#1253)
* Add depth data loading for polycam datasets

* misc: missing arguments in process_data_utils.downscale_images

* Move processing to polycam_utils

* delete unused imports

* process_data_utils: patch for frame%05d issue

* accidentally deleted neighbor flag from ffmpeg

* wrong ffmpeg command

* upscale directly

* redundant comment

* remove unused imports

* black formatting
2023-01-24 14:45:13 -08:00
cvachha 9eb880aa91 Blender addon script and documentation (#1218)
* Blender addon script and documentation

First version of blender addon python script located in scripts/blender and new documentation for the addon. The Blender addon is for importing or exporting a camera path for visual effects and compositing.

* Updated formatting of Blender script

Updated the formatting based on the script tests for the blender addon script.

* Updated Blender addon to fix FOV and alignment

Updated how FOV is calculated for both blender cam to json and json to blender cam. The FOV is calculated based on the aspect ratio, angle of view, and sensor fit and size.

* Updated Blender addon documentation with examples

Updated the Blender add-on documentation with a few example gif composite animations

* Updated Blender addon to match frame rate and fixed formatting

Updated the Blender add-on script and docs to match the Blender frame rate. Also the formatting should be fixed. There are also now error message popups instead of console prints for invalid input in the add-on.

* Updated the blender addon for formatting

Updated pylint formatting and comments
2023-01-19 22:31:07 -08:00
Matthew Tancik af41819611 Add support for RealityCapture (#1055)
* Add support for RealityCapture

* Fix coordinate bug

* Remove transform

* Update focal lengths

* isort
2023-01-19 20:50:02 -08:00
machenmusik f350650f1b create video writer later, to adapt to render image's width and height (fixes #1242) (#1245)
* create video writer later, to adapt to render image's width and height

* fix rendering with multiple output names
2023-01-17 09:40:26 -08:00
Matthew Tancik 5b50740f45 Add cropping options to data processing (#1236) 2023-01-16 15:34:20 -08:00
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
Martin Piala a5eea5f14d Camera export (#1191)
* implement the camera exporter

* remove train_dataset from exporter

* fix linter errors

* add docstring

* correct comment

* fix linter errors

* make image_filenames a property of the dataset
2022-12-31 22:38:43 -07:00
Jake Austin 3ffee522e0 TrainerConfig inherit from InstantiateConfig (#1175)
Making TrainerConfig an InstantiateConfig so it can be swapped in and out with different methods. Also made the TrainerConfig a subclass of ExperimentConfig (which was changed from a printableconfig to an instantiateconfig), since we were already instantiating the Trainer class with the ExperimentConfig

Removed the "config" field from the TrainerCallbackAttributes struct to eliminate circular dependencies when types are checked.

Minor scripts and docs changes to accommodate the update to the config struct, meaning the flags that were associated with the TrainerConfig were moved up to the top level of the config.
2022-12-27 18:19:34 -10:00
Brent Yi 5495a8e146 Type and docs fixes (#1170) 2022-12-26 09:04:24 -07:00
Matthew Tancik 4a27e5e929 Fix downscaling and type errors (#1164) 2022-12-23 14:07:07 -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
Ethan Weber 3bf490e845 adding data subset (#1135)
* adding nerfstudio-dataset

* removed file
2022-12-15 17:29:41 -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
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
RandomPrototypesandRandomPrototypes 740cdebbb5 WIP : support for hloc toolbox (superpoint, superglue, netvlad,...) (#1026)
* basic support for hloc (includes netvlad, super point, superglue in colmap), just a first test, not ready yet

* add exhaustive match option for hloc

* add command line option to choose the type of feature, matcher,...

* make hloc an optional dependency, update doc, and small bug fixes

* fix missing imports

* fix warnings, pylint,...

* fix overwrite previous commits

* fix import order from isort

* move find_tool_feature_matcher_combination to process_data_utils, add type hints and Args/Returns doc

* error message when no valid combination of sfm tool, feature type, and matcher

Co-authored-by: RandomPrototypes <delmotte_ar@yahoo.fr>
2022-12-03 22:45:48 -08:00
Ethan Weber 3377c5344b [WIP] Mesh export UI (#1076)
* starting PR

* export mesh ui functional

* better descriptions
2022-12-02 17:51:21 -08:00