#dmytrotweetsaboutdl — Public Fediverse posts

Enjoy Image Matching Challenge 2023 recap:

https://ducha-aiki.github.io/wide-baseline-stereo-blog/2023/07/05/IMC2023-Recap.html

tl;dr:
- SfM is not solved
- global desc similarity is hard
- orientation invariance for SuperGlue is easy
- PixSfM is good idea, but need follow-ups
- KeyNetAffNet
@kornia_foss rocks

#IMC2023 #CVPR2023

@cvpr

#computervision #deeplearning
#dmytrotweetsaboutDL

D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers

Jianfeng He, Yuan Gao, Tianzhu Zhang, Zhe Zhang, Feng Wu

tl;dr: no idea how that works, hierarchical attention something. No eval on #IMC

https://openaccess.thecvf.com/content/CVPR2023/papers/He_D2Former_Jointly_Learning_Hierarchical_Detectors_and_Contextual_Descriptors_via_Agent-Based_CVPR_2023_paper.pdf
#CVPR2023
#computervision #deeplearning
#dmytrotweetsaboutDL

SFD2: Semantic-guided Feature Detection and Description

Fei Xue, Ignas Budvytis, Roberto Cipolla

tl;dr: more principled approach to use segmentation for image matching, than class-name filtering.

https://arxiv.org/abs/2304.14845.pdf

#computervision #deeplearning
#dmytrotweetsaboutDL
#CVPR2023

PMatch: Paired Masked Image Modeling for Dense Geometric Matching

Shengjie Zhu, Xiaoming Liu

tl;dr: cross-view patch reconstruction pre training, then use (modified) LoFTR for two view matching.
Code repo is not yet created.
https://arxiv.org/abs/2303.17342.pdf
#computervision #deeplearning
#dmytrotweetsaboutDL #CVPR2023

3D Line Mapping Revisited

Shaohui Liu, Yifan Yu, Rémi Pautrat, Marc Pollefeys, Viktor Larsson

tl;dr: Point-guided line SfM with scale-invariant scoring -> profit. Even improves SuperPoint + Colmap bundle adjustment

https://arxiv.org/abs/2303.17504.pdf

#CVPR2023

#computervision #deeplearning
#dmytrotweetsaboutDL #CVPR2023

ParaFormer: Parallel Attention Transformer for Efficient Feature Matching

Xiaoyong Lu, Yaping Yan, Bin Kang, Songlin Du

tl;dr: new architecture for SuperGlue. No eval on #IMC

https://arxiv.org/abs/2303.00941

#computervision #deeplearning
#dmytrotweetsaboutDL

AdaSfM: From Coarse Global to Fine Incremental Adaptive Structure from Motion

Yu Chen, Zihao Yu, Shu Song, Tianning Yu, Jianming Li, Gim Hee Lee

tl;dr: split view-graph into smaller with IMU sensors,use incremental SfM locally, global globally

https://arxiv.org/abs/2301.12135
#ICRA2023

#computervision #deeplearning
#dmytrotweetsaboutDL