This website requires JavaScript.
a2f76b5823
optimize the running speed of mask_processor node
original
wTechArtist
2025-06-23 18:07:29 +08:00
55016bac45
optimize bounding box
wTechArtist
2025-06-21 23:01:17 +08:00
ed426b762b
WIP: working on optimizations
weiweiliang
2025-06-21 18:50:36 +08:00
fae45e83a3
optimize code
wTechArtist
2025-06-21 18:49:30 +08:00
8f6f15676b
update
wTechArtist
2025-06-20 15:38:04 +08:00
5ee5e5dcc2
update
wTechArtist
2025-06-20 15:16:44 +08:00
6a1732b2dc
update
wTechArtist
2025-06-20 14:22:12 +08:00
eeed84de32
update
wTechArtist
2025-06-19 17:28:18 +08:00
1df29d4da7
update
wTechArtist
2025-06-18 16:25:59 +08:00
0dc115fd23
update
wTechArtist
2025-06-18 15:02:10 +08:00
1e5b620e92
update
wTechArtist
2025-06-18 11:40:19 +08:00
93632600a7
update: 合并README文件,删除冗余文档
wTechArtist
2025-06-18 09:57:28 +08:00
a9304a8c0d
update
wTechArtist
2025-06-16 21:10:48 +08:00
a682be12b2
update
wTechArtist
2025-06-16 18:47:16 +08:00
e11ce8a361
original
wTechArtist
2025-05-30 14:51:02 +08:00
f120e9e966
调整箭头长度显示:增加基准长度到15%,范围8%-20%,提升可视化效果
main
weiweiliang
2025-05-29 21:08:21 +08:00
6d70090081
修复VGGT箭头长度问题: 使用相对长度避免箭头射出画面外
weiweiliang
2025-05-29 20:33:52 +08:00
e1f9d3aa65
更新VGGT节点: 使用3D立体轨迹可视化,与COLMAP节点保持一致的视觉效果
weiweiliang
2025-05-29 20:26:38 +08:00
ae725d04bd
Clean up: Remove unnecessary files, keep only ComfyUI node essentials
master
weiweiliang
2025-05-29 18:34:22 +08:00
ac738c88bd
Initial commit
wTechArtist
2025-05-29 18:26:23 +08:00
22d5c18fe6
[WIP] Upload demo_colmap.py, which can (a) run both vggt and vggt+ba, (b) output in a colmap format, (c) in the original image resolution. The output can be directly used for nerf/gaussian training.
Jianyuan Wang
2025-05-22 23:27:58 +01:00
a9f0fa7d6b
[WIP] Upload demo_colmap.py, which can (a) run both vggt and vggt+ba, (b) output in a colmap format, (c) in the original image resolution. The output can be directly used for nerf/gaussian training.
Jianyuan Wang
2025-05-22 23:24:25 +01:00
c4b5da2d85
Merge pull request #125 from D31T4/main
Jianyuan Wang
2025-05-08 11:22:48 +01:00
3d56b6b6bc
Avoid using np allow_pickle for Deserialization
Jianyuan Wang
2025-05-07 16:28:25 +01:00
3fc15eadda
fix vggt_to_colmap images.bin output format
D31T4
2025-05-07 14:06:24 +10:00
b017d60f32
upload eval code for co3d
jianyuan
2025-05-03 16:38:45 +00:00
51ee022e3d
Merge pull request #112 from Vincentqyw/main
Jianyuan Wang
2025-04-28 02:20:27 +01:00
65c1f4ed54
fix: use float32 in pos embed for MPS compatibility
Realcat
2025-04-24 17:40:45 +00:00
350abfcdc6
fix: use float32 in pos embed for MPS compatibility
Realcat
2025-04-24 17:36:37 +00:00
588a0a238d
update the news about training code
Jianyuan Wang
2025-04-13 05:19:31 +01:00
7260ede3ff
Merge pull request #86 from djecoo/python_version_uv
Jianyuan Wang
2025-04-11 00:37:47 +01:00
35e65de083
Update uv python version
djecoo
2025-04-06 11:02:54 +02:00
b02cc03cee
VGGT to COLMAP format converter (Merge pull request #42 from atakan-topaloglu/main)
Jianyuan Wang
2025-03-30 04:31:51 +01:00
81ddb97ad4
Fix: Removed old colmap_writer.py
Atakan Topaloglu
2025-03-30 01:46:49 +03:00
30180e6e71
Fix: Works for arbitrary captures (not only orbital captures) with bin support, faster and memory efficient point cloud storage, sky and background filtering
Atakan Topaloglu
2025-03-29 18:50:53 +03:00
5c91b0169e
Sky filtering works, remove the temp directories and save the final model
Atakan Topaloglu
2025-03-29 18:12:24 +03:00
009d8515d1
Last commit beofre following the convention of visual_util.py
Atakan Topaloglu
2025-03-29 17:34:34 +03:00
daf7f94ba4
Sky filtering, and bw filtering works, regression tests run. Will try making confidence filtering identical to that of VGGT
Atakan Topaloglu
2025-03-29 16:49:25 +03:00
3cf03416c3
Color works, smoke test passed, add filter background and sky options. Todo: better confidence thresholding
Atakan Topaloglu
2025-03-29 16:28:51 +03:00
8aa0832859
Fix the incorrect camera poses and added .bin COLMAP exports, point cloud still in grayscale
Atakan Topaloglu
2025-03-29 16:18:39 +03:00
6d361a374e
Merge pull request #57 from yashbhalgat/yash-preproc-fix
Jianyuan Wang
2025-03-25 23:07:46 +00:00
b4b73db60d
Merge pull request #55 from pablovela5620/main
Jianyuan Wang
2025-03-25 22:59:40 +00:00
692096e818
Add 'pad' mode in preprocessing to handle cases where height is greater than width
yashbhalgat
2025-03-25 13:05:23 +00:00
467690acac
Update pyproject.toml
Pablo Vela
2025-03-24 14:57:00 -05:00
1a14b2d0e2
Update pyproject.toml
Pablo Vela
2025-03-24 14:52:22 -05:00
6830466c42
Update pyproject file to allow all numpy<2
Jianyuan Wang
2025-03-23 21:50:05 +00:00
b66eeb36b5
provide details to install vggt as a package
jianyuan
2025-03-23 20:25:58 +00:00
16d54825a5
provide details to install vggt as a package
jianyuan
2025-03-23 20:24:54 +00:00
e35b89ac6a
provide details to install vggt as a package
jianyuan
2025-03-23 20:22:43 +00:00
01e5d11e2a
update pyproject and readme
jianyuan
2025-03-23 20:14:54 +00:00
4d9710fb2e
update pyproject and readme
jianyuan
2025-03-23 20:07:49 +00:00
4e321b8a8c
Add pyproject.toml to allow easy installion
Jianyuan Wang
2025-03-23 19:51:17 +00:00
f8bf73ac25
update numpy version constraint to allow for compatibility with future releases
pablovela5620
2025-03-23 14:28:55 -05:00
a6ba138800
relax torch + torchvision version requirements
pablovela5620
2025-03-23 14:27:57 -05:00
d33e01ee13
update installation instructions in README.md for pip, pixi, and uv
pablovela5620
2025-03-23 14:22:52 -05:00
ce841d7dc0
add proper pyproject.toml
pablovela5620
2025-03-23 14:12:42 -05:00
a16b0760f6
add instruction about masking
Jianyuan Wang
2025-03-22 18:09:30 +00:00
a902743b97
Changed gitignore for compatibility with main branch
Atakan Topaloglu
2025-03-20 21:29:17 +03:00
74213fcd52
Added confidence thresholding to colmap_writer.py
Atakan Topaloglu
2025-03-20 21:28:06 +03:00
0d31386f53
Remove file from remote
Atakan Topaloglu
2025-03-20 21:10:58 +03:00
67b02db572
Added colmap writer for point cloud and camera initialization
Atakan Topaloglu
2025-03-20 21:08:48 +03:00
3fba88d5bf
Merge remote-tracking branch 'upstream/main'
Atakan Topaloglu
2025-03-20 20:55:36 +03:00
ae1b9c8750
update tensor contiguous for dpt head
Jianyuan Wang
2025-03-20 17:42:14 +00:00
4b14330514
Point cloud and camera estimation works well
Atakan Topaloglu
2025-03-20 20:08:51 +03:00
497e1bade4
add single view results from Karim Abou Zeid
Jianyuan Wang
2025-03-19 22:36:04 +00:00
0440b430f1
add single view results from Karim Abou Zeid
Jianyuan Wang
2025-03-19 22:34:40 +00:00
fa5911cb6b
Fix the problem that some old gpus do not support bfloat16
Jianyuan Wang
2025-03-19 03:54:29 +00:00
aeccf2ef2f
Fix the problem that some old gpus do not support bfloat16
Jianyuan Wang
2025-03-19 03:53:36 +00:00
9d7f328ded
Update demo_gradio.py
Jianyuan Wang
2025-03-19 01:38:28 +00:00
ee7c20a03f
Update README.md
Jianyuan Wang
2025-03-19 01:35:29 +00:00
a5ffa7e00a
Merge pull request #22 from mateosss/mateosss
Jianyuan Wang
2025-03-18 20:04:13 +00:00
752a1fbc39
Merge pull request #26 from kabouzeid/patch-1
Jianyuan Wang
2025-03-18 19:39:52 +00:00
0d48170324
Update requirements_demo.txt
Karim Abou Zeid
2025-03-18 20:36:23 +01:00
e00e72765a
Update requirements
Mateo de Mayo
2025-03-18 16:45:39 +01:00
61020e2751
Alignment is upside down, likely due to poor initialization
Atakan Topaloglu
2025-03-18 15:55:51 +03:00
7efebaba5a
npz reader works, reconstruction fails, alignment wo overlapping camera poses
Atakan Topaloglu
2025-03-18 15:06:47 +03:00
f26cfc96be
solve the problem that pytorch will ignore dtype = torch.bfloat16 if bfloat not supported
jianyuan
2025-03-18 04:12:19 +00:00
56e693172d
add function documents; re-format
jianyuan
2025-03-17 23:31:23 +00:00
f1bc88b9f0
update project page
jianyuan
2025-03-17 01:30:53 +00:00
40eb1c5cf3
Initial commit
jianyuan
2025-03-16 23:04:25 +00:00