Dmytro Mishkin
@ducha-aiki.bsky.social
Marrying classical CV and Deep Learning. I do things, which work, rather than being novel, but not working.
http://dmytro.ai
http://dmytro.ai
SAM 3D: 3Dfy Anything in Images
SAM 3D Team et al?
tl;dr: in title. 8-stage training, dataset, human labeling. Do not read tl;dr, read whole paper
arxiv.org/abs/2511.16624
SAM 3D Team et al?
tl;dr: in title. 8-stage training, dataset, human labeling. Do not read tl;dr, read whole paper
arxiv.org/abs/2511.16624
November 21, 2025 at 1:00 PM
SAM 3D: 3Dfy Anything in Images
SAM 3D Team et al?
tl;dr: in title. 8-stage training, dataset, human labeling. Do not read tl;dr, read whole paper
arxiv.org/abs/2511.16624
SAM 3D Team et al?
tl;dr: in title. 8-stage training, dataset, human labeling. Do not read tl;dr, read whole paper
arxiv.org/abs/2511.16624
POMA-3D: The Point Map Way to 3D Scene Understanding
Weixun Luo, Ranran Huang, Junpeng Jing, Krystian Mikolajczyk
tl;dr: in title + dataset.
arxiv.org/abs/2511.16567
Weixun Luo, Ranran Huang, Junpeng Jing, Krystian Mikolajczyk
tl;dr: in title + dataset.
arxiv.org/abs/2511.16567
November 21, 2025 at 12:53 PM
POMA-3D: The Point Map Way to 3D Scene Understanding
Weixun Luo, Ranran Huang, Junpeng Jing, Krystian Mikolajczyk
tl;dr: in title + dataset.
arxiv.org/abs/2511.16567
Weixun Luo, Ranran Huang, Junpeng Jing, Krystian Mikolajczyk
tl;dr: in title + dataset.
arxiv.org/abs/2511.16567
PartUV: Part-Based UV Unwrapping of 3D Meshes
Zhaoning Wang, Xinyue Wei, Ruoxi Shi, Xiaoshuai Zhang, Hao Su, Minghua Liu
arxiv.org/abs/2511.16659
tl;dr: in-title, start from learning-based split -> algorithmic finish
Zhaoning Wang, Xinyue Wei, Ruoxi Shi, Xiaoshuai Zhang, Hao Su, Minghua Liu
arxiv.org/abs/2511.16659
tl;dr: in-title, start from learning-based split -> algorithmic finish
November 21, 2025 at 12:49 PM
PartUV: Part-Based UV Unwrapping of 3D Meshes
Zhaoning Wang, Xinyue Wei, Ruoxi Shi, Xiaoshuai Zhang, Hao Su, Minghua Liu
arxiv.org/abs/2511.16659
tl;dr: in-title, start from learning-based split -> algorithmic finish
Zhaoning Wang, Xinyue Wei, Ruoxi Shi, Xiaoshuai Zhang, Hao Su, Minghua Liu
arxiv.org/abs/2511.16659
tl;dr: in-title, start from learning-based split -> algorithmic finish
SatAst benchmark, I love it
November 20, 2025 at 9:21 AM
SatAst benchmark, I love it
RoMa v2 results.
November 20, 2025 at 9:08 AM
RoMa v2 results.
RoMa v2: Harder Better Faster Denser Feature Matching
@parskatt.bsky.social et 11 al.
tl;dr: in title.
Predict covariance per-pixel, more datasets, use DINOv3, adjust architecture.
arxiv.org/abs/2511.15706
@parskatt.bsky.social et 11 al.
tl;dr: in title.
Predict covariance per-pixel, more datasets, use DINOv3, adjust architecture.
arxiv.org/abs/2511.15706
November 20, 2025 at 9:08 AM
RoMa v2: Harder Better Faster Denser Feature Matching
@parskatt.bsky.social et 11 al.
tl;dr: in title.
Predict covariance per-pixel, more datasets, use DINOv3, adjust architecture.
arxiv.org/abs/2511.15706
@parskatt.bsky.social et 11 al.
tl;dr: in title.
Predict covariance per-pixel, more datasets, use DINOv3, adjust architecture.
arxiv.org/abs/2511.15706
DA3
Architecture and prediction target ablations
3/3
Architecture and prediction target ablations
3/3
November 17, 2025 at 4:45 PM
DA3
Architecture and prediction target ablations
3/3
Architecture and prediction target ablations
3/3
DA3 2/3
Synthetic teacher == DAv2-like model to process real world datasets like MegaDepth, and get them dense and sharp depth.
Also great section of dataset issues in Appendix
Synthetic teacher == DAv2-like model to process real world datasets like MegaDepth, and get them dense and sharp depth.
Also great section of dataset issues in Appendix
November 17, 2025 at 4:45 PM
DA3 2/3
Synthetic teacher == DAv2-like model to process real world datasets like MegaDepth, and get them dense and sharp depth.
Also great section of dataset issues in Appendix
Synthetic teacher == DAv2-like model to process real world datasets like MegaDepth, and get them dense and sharp depth.
Also great section of dataset issues in Appendix
Depth Anything 3: Recovering the Visual Space from Any Views
Haotong Lin, Sili Chen, Junhao Liew, Donny Y. Chen, Zhenyu Li, Guang Shi, Jiashi Feng, Bingyi Kang
tl;dr: DINOv2+reshape for multiview,
joint DPT, synth teacher. Depth-ray output.
Simpler VGGT.
arxiv.org/abs/2511.10647
Haotong Lin, Sili Chen, Junhao Liew, Donny Y. Chen, Zhenyu Li, Guang Shi, Jiashi Feng, Bingyi Kang
tl;dr: DINOv2+reshape for multiview,
joint DPT, synth teacher. Depth-ray output.
Simpler VGGT.
arxiv.org/abs/2511.10647
November 17, 2025 at 4:45 PM
Depth Anything 3: Recovering the Visual Space from Any Views
Haotong Lin, Sili Chen, Junhao Liew, Donny Y. Chen, Zhenyu Li, Guang Shi, Jiashi Feng, Bingyi Kang
tl;dr: DINOv2+reshape for multiview,
joint DPT, synth teacher. Depth-ray output.
Simpler VGGT.
arxiv.org/abs/2511.10647
Haotong Lin, Sili Chen, Junhao Liew, Donny Y. Chen, Zhenyu Li, Guang Shi, Jiashi Feng, Bingyi Kang
tl;dr: DINOv2+reshape for multiview,
joint DPT, synth teacher. Depth-ray output.
Simpler VGGT.
arxiv.org/abs/2511.10647
Great overview of the workshops and tutorials.
My favorites:
1) CAD representation
2) synthetic data to help city-scale reconstruction
3) trends in 3D vision
4) visual chain-of-thoughts?
My favorites:
1) CAD representation
2) synthetic data to help city-scale reconstruction
3) trends in 3D vision
4) visual chain-of-thoughts?
November 3, 2025 at 1:06 PM
Great overview of the workshops and tutorials.
My favorites:
1) CAD representation
2) synthetic data to help city-scale reconstruction
3) trends in 3D vision
4) visual chain-of-thoughts?
My favorites:
1) CAD representation
2) synthetic data to help city-scale reconstruction
3) trends in 3D vision
4) visual chain-of-thoughts?
I HATE long @bsky.app name-handles.
Common, exclude them from the char limit, or whatever.
On twitter, when authors are on platform, it means MORE space. Here is means LESS space
It is easy to fit the paper name + authors (handles) + tl;dr + arXiv link on twitter, but almost impossible here :(
Common, exclude them from the char limit, or whatever.
On twitter, when authors are on platform, it means MORE space. Here is means LESS space
It is easy to fit the paper name + authors (handles) + tl;dr + arXiv link on twitter, but almost impossible here :(
November 3, 2025 at 1:00 PM
I HATE long @bsky.app name-handles.
Common, exclude them from the char limit, or whatever.
On twitter, when authors are on platform, it means MORE space. Here is means LESS space
It is easy to fit the paper name + authors (handles) + tl;dr + arXiv link on twitter, but almost impossible here :(
Common, exclude them from the char limit, or whatever.
On twitter, when authors are on platform, it means MORE space. Here is means LESS space
It is easy to fit the paper name + authors (handles) + tl;dr + arXiv link on twitter, but almost impossible here :(
Scaling Image Geo-Localization to Continent Level
Philipp Lindenberger
@pesarlin.bsky.social @janhosang.bsky.social Matteo Balice @marcpollefeys.bsky.social Simon Lynen, Eduard Trulls
tl;dr: combine ground+aerial to get cell-prototype. Acc@ 42Gb = ground [email protected]
arxiv.org/abs/2510.26795
Philipp Lindenberger
@pesarlin.bsky.social @janhosang.bsky.social Matteo Balice @marcpollefeys.bsky.social Simon Lynen, Eduard Trulls
tl;dr: combine ground+aerial to get cell-prototype. Acc@ 42Gb = ground [email protected]
arxiv.org/abs/2510.26795
November 3, 2025 at 12:56 PM
Scaling Image Geo-Localization to Continent Level
Philipp Lindenberger
@pesarlin.bsky.social @janhosang.bsky.social Matteo Balice @marcpollefeys.bsky.social Simon Lynen, Eduard Trulls
tl;dr: combine ground+aerial to get cell-prototype. Acc@ 42Gb = ground [email protected]
arxiv.org/abs/2510.26795
Philipp Lindenberger
@pesarlin.bsky.social @janhosang.bsky.social Matteo Balice @marcpollefeys.bsky.social Simon Lynen, Eduard Trulls
tl;dr: combine ground+aerial to get cell-prototype. Acc@ 42Gb = ground [email protected]
arxiv.org/abs/2510.26795
BASIC dataset info and annotators salary conditions -- employed workers.
2/2
2/2
November 3, 2025 at 12:53 PM
BASIC dataset info and annotators salary conditions -- employed workers.
2/2
2/2
Instance-Level Composed Image Retrieval
@billpsomas.bsky.social George Retsinas @nikos-efth.bsky.social Panagiotis Filntisis,Yannis Avrithis, Petros Maragos, Ondrej Chum, @gtolias.bsky.social
tl;dr: condition-based retrieval (+dataset) - old photo/sunset/night/aerial/model arxiv.org/abs/2510.25387
@billpsomas.bsky.social George Retsinas @nikos-efth.bsky.social Panagiotis Filntisis,Yannis Avrithis, Petros Maragos, Ondrej Chum, @gtolias.bsky.social
tl;dr: condition-based retrieval (+dataset) - old photo/sunset/night/aerial/model arxiv.org/abs/2510.25387
November 3, 2025 at 12:53 PM
Instance-Level Composed Image Retrieval
@billpsomas.bsky.social George Retsinas @nikos-efth.bsky.social Panagiotis Filntisis,Yannis Avrithis, Petros Maragos, Ondrej Chum, @gtolias.bsky.social
tl;dr: condition-based retrieval (+dataset) - old photo/sunset/night/aerial/model arxiv.org/abs/2510.25387
@billpsomas.bsky.social George Retsinas @nikos-efth.bsky.social Panagiotis Filntisis,Yannis Avrithis, Petros Maragos, Ondrej Chum, @gtolias.bsky.social
tl;dr: condition-based retrieval (+dataset) - old photo/sunset/night/aerial/model arxiv.org/abs/2510.25387
Not sift points, but other region detector.
The issue though, is that some areas are over-represented, whereas others, also important, but textureless, have no voice.
The issue though, is that some areas are over-represented, whereas others, also important, but textureless, have no voice.
October 22, 2025 at 1:11 PM
Not sift points, but other region detector.
The issue though, is that some areas are over-represented, whereas others, also important, but textureless, have no voice.
The issue though, is that some areas are over-represented, whereas others, also important, but textureless, have no voice.
October 21, 2025 at 6:44 PM
LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching
Aidyn Ubingazhibov, Rémi Pautrat, Iago Suárez,
Shaohui Liu, @marcpollefeys.bsky.social , Viktor Larsson
tl;dr: Better and faster gluestick with line attention.
arxiv.org/abs/2510.16438
Aidyn Ubingazhibov, Rémi Pautrat, Iago Suárez,
Shaohui Liu, @marcpollefeys.bsky.social , Viktor Larsson
tl;dr: Better and faster gluestick with line attention.
arxiv.org/abs/2510.16438
October 21, 2025 at 6:03 PM
LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching
Aidyn Ubingazhibov, Rémi Pautrat, Iago Suárez,
Shaohui Liu, @marcpollefeys.bsky.social , Viktor Larsson
tl;dr: Better and faster gluestick with line attention.
arxiv.org/abs/2510.16438
Aidyn Ubingazhibov, Rémi Pautrat, Iago Suárez,
Shaohui Liu, @marcpollefeys.bsky.social , Viktor Larsson
tl;dr: Better and faster gluestick with line attention.
arxiv.org/abs/2510.16438
October 21, 2025 at 3:23 AM
Take-away messages and Open Problems from RANSAC in 2025 tutorial.
October 21, 2025 at 3:16 AM
Take-away messages and Open Problems from RANSAC in 2025 tutorial.
October 21, 2025 at 2:20 AM
Nabla-RANSAC vs NG-DSAC
October 21, 2025 at 2:04 AM
Nabla-RANSAC vs NG-DSAC
Optimist vs realist in RANSAC
October 21, 2025 at 1:52 AM
Optimist vs realist in RANSAC