nerfstudio

0 Fork 0

mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-12 19:04:03 +08:00

Author	SHA1	Message	Date
Jake Austin jake-austin@berkeley.edu	35be6fd421	Accounting for camera distortion, caching undistorted images	2023-09-18 10:13:43 +00:00
Jake Austin jake-austin@berkeley.edu	b24835d55f	More config	2023-09-16 07:48:37 +00:00
Jake Austin jake-austin@berkeley.edu	8c2b1b8535	Configifying scene extent	2023-09-16 07:38:02 +00:00
Jake Austin jake-austin@berkeley.edu	f6bdfacf56	Configify	2023-09-16 07:34:18 +00:00
Jake Austin jake-austin@berkeley.edu	274d8f2215	Adding another TODO	2023-09-16 05:28:03 +00:00
Jake Austin jake-austin@berkeley.edu	2ea816cf6a	Fixed callbacks causing no splits	2023-09-16 04:57:36 +00:00
Jake Austin jake-austin@berkeley.edu	0e1c8f084d	Everything implemented but needs testing	2023-09-16 04:57:36 +00:00
Zhuoyang	e3a0f0296c	fix small bugs and allow testing on images with aspect-ratio not equal to 1	2023-09-14 13:44:23 -07:00
Brent Yi	9c061f2a99	Config fixes	2023-09-12 18:18:38 -07:00
Jake Austin jake-austin@berkeley.edu	e5873d8dba	Going back to original code for speed of testing and correctness for now	2023-09-12 23:27:56 +00:00
Jake Austin jake-austin@berkeley.edu	1a214ba129	Temp save	2023-09-12 23:19:47 +00:00
Jake Austin jake-austin@berkeley.edu	8bf21213f1	Adding more TODOs	2023-09-12 03:38:21 +00:00
Jake Austin jake-austin@berkeley.edu	bb90b94fb0	Basic working, still needs to be profiled and tuned, some preliminary TODOs labeled 'jake-austin' need to be addressed	2023-09-12 03:15:11 +00:00
Jake Austin jake-austin@berkeley.edu	749059d4fb	First pass at dataloader, set up file structure (minus the actual rendering code)	2023-09-08 17:55:46 +00:00
Zhensheng YuanandMatthew Tancik	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
elenacliuandAdamRashid96	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 Sasha Sax Ethan Weber AdamRashid96 AdamRashid96	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
MocaxandMatthew Tancik	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 XuandMatthew Tancik	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 ) v0.3.3	2023-08-17 11:59:04 -07:00
Sasha SaxandMatthew Tancik	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
Brent Yi	6d51af1a24	viser 0.1.0, fix type checker errors (#2343 ) * Pin to viser 0.1.0, fix type checker errors * gui_folder => add_gui_folder	2023-08-15 23:15:35 +00:00
Justin Kerr	5de83ac50a	Circle crop to images processing pipeline (#2341 ) add circle crop to images data processing pipeline	2023-08-15 14:32:44 +09:00
elenacliu	bc8341378a	fix #2318 : add train/test/eval split for instant ngp dataparser (#2335 ) * fix #2318: add train/test/eval split for instant ngp dataparser * fix: instant_ngp_dataparser.py format	2023-08-14 04:24:34 +00:00
Haoyuan Wang	3455fb749f	fix: ColmapDataParser downscaling images error. (#2337 )	2023-08-13 21:16:47 -07:00
Kate Yurkova	c599d0f3a1	fix: Allow custom user ID (#2334 )	2023-08-12 20:17:38 +00:00
Kate Yurkova	5eb83e8acd	Account for `num_gpus` rename in docs + test configs (#2332 ) * fix: num-gpus to num-devices * fix: Update test_config1.yml * fix: Update test_config2.yml	2023-08-12 11:09:44 +00:00
Matias Turkulainen	4fe8e657d2	Rename num_cameras to camera_indices (#2326 ) rename num_cameras -> camera_indices	2023-08-10 15:36:01 -07:00
machenmusik	cb2405d3ea	When generating depth images, use torch_compile with ZoeDepth for compatibility (#2303 ) * Use torch_compile with Zoe for compatibility torch_compile module support Previously the compatibility utility torch.compile worked for functions, but not for modules as torch.compile was originally employed here. * torch_compile -> Any	2023-08-09 17:08:17 -07:00
Matias Turkulainen	cf2d90d009	template repository (#2319 ) * template repo * template repo	2023-08-09 17:01:48 +00:00
Ethan Weberandmachenmusik	9b6010ea0d	Adding support for PairPixelSampler and PatchPixelSampler masks (#2305 ) * changes * pair pixel sampling with a mask * reverting changes * revert changes * remove line in erode * support for patch pixel samplerr masks * fix --------- Co-authored-by: machenmusik <machenmusik@users.noreply.github.com>	2023-08-05 10:40:23 -04:00
Matthew Tancik	50d8c7ba7d	Add sponsors (#2307 )	2023-08-04 15:07:44 -04:00
AdamRashid96 Matthew Tancik Ethan Weber Ethan Weber	7e90cb7989	PixelSampler Fixes (#2298 ) * monodepth implemented * device * pair pixel sampler * docstring * removing unused imports * fix bugs * cache in cache dir, no longer edit json file * moving to depth nerfacto * fixed bug using median depth by accident * removing depthdataset from nerfacto * added pixelsamplerconfig * added equirectangular warning back * bug fix * delete sample_config.py + small fixes * rename to pixel_sampler * cleaning * test * passing num_rays_per_batch properly * fixed transforms typo * renaming in nerfacto * remove depth files from test data * removed defaulting to base pixel sampler with mask * adding patch_size back * Warning for notimplemented error and patch_size fix * fix config.pixel_sampler check --------- Co-authored-by: Matthew Tancik <tancik@berkeley.edu> Co-authored-by: Ethan Weber <ethanweber@berkeley.edu> Co-authored-by: Ethan Weber <eweb0124@gmail.com>	2023-08-04 10:27:35 -04:00
Frederik WarburgandEthan Weber	9b03299d40	Train and eval data splits (Nerfbusters) (#2207 ) * nerfbusters dataparser * nerfbuster dataparser and visualization of eval views * resolved some errors from pyright * enable ns-process-data to take two videos as input and use one for eval and the other for train * resolve some pyright issues * instead of data being a tuple, I added eval_data as another argument * implemented train eval split for all cases * implemented train eval split for all cases * reverting equi changes * reverting reality capture changes * raise valueerror * revert comment * added split override code back to dataparser * reverted one change * using image border now * adding docs --------- Co-authored-by: Ethan Weber <eweb0124@gmail.com>	2023-08-04 10:11:55 -04:00
machenmusik	388fcb09e1	convert raw to JPG not TIFF, to avoid fast-downscale ffmpeg error (#2295 )	2023-08-02 09:44:35 -07:00
machenmusik	5b4abc41e6	Allow same dimensions optimizations to be disabled (#2292 ) Use ns-process-data images --no-same-dimensions ... to handle images sets with different dimensions properly. (Fast downscaling assumes image dimensions are the same.)	2023-08-01 23:35:27 -07:00
Ethan Weber AdamRashid96 Matthew Tancik	71c6b9cf3d	Monodepth Regularization (#2284 ) * monodepth implemented * device * pair pixel sampler * docstring * removing unused imports * fix bugs * cache in cache dir, no longer edit json file * moving to depth nerfacto * fixed bug using median depth by accident * removing depthdataset from nerfacto * added pixelsamplerconfig * added equirectangular warning back * bug fix * delete sample_config.py + small fixes * rename to pixel_sampler * cleaning * test * passing num_rays_per_batch properly * fixed transforms typo * renaming in nerfacto * remove depth files from test data * removed defaulting to base pixel sampler with mask * adding patch_size back --------- Co-authored-by: AdamRashid96 <abrashid@berkeley.edu> Co-authored-by: Matthew Tancik <tancik@berkeley.edu>	2023-08-01 18:52:47 -07:00
Brent Yi	72da747fc2	Remove system-level CUDA install from install instructions (#2289 ) * Remove system-level CUDA install from Linux install instructions * Remove system-level CUDA from Windows install instructions * Un-flip CUDA 11.7 / 11.8	2023-08-01 22:50:22 +00:00
Brent Yi	dab39c25b4	More robust install instructions (#2277 ) Add cuda-toolkit install to readme/docs	2023-08-01 20:35:22 +00:00
AX-I	98d36ed7d9	Option to process images on GPU for speed at the expense of memory (#2288 ) * Fix pixel sampler cpu bottleneck cpu usage reduced 1700% -> 100%, and even more if using multi-gpu training * Convert to config option * Change optional to bool	2023-08-01 11:12:30 -07:00

1 2 3 4 5 ...