arXiv Computer Vision
SGFormer: Structure-Guided Transformer for Robust Local Feature Matching
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Aug 4
SGFormer: Structure-Guided Transformer for Robust Local Feature Matching
Local feature matching is a fundamental component of photogrammetry, enabling accurate image correspondence critical for tasks such as 3D reconstruction, stereo mapping, and visual localization. While recent detector-free matching methods, like LoFTR, have advanced the field, the global features obtained by leveraging the global-range modeling capacity of the unconstrained attention mechanism compromise the model's attention to the salient structures in certain scenarios.
arXiv Computer Vision
Aug 25
StereoDiffuer: Diffusion-based Progressive Geometry Modeling with Saliency Attention Perception for Stereo Matching
arXiv:2608.21710v1 Announce Type: new Abstract: With the advance of deep neural networks, the quality of disparity maps obtained through stereo matching has steadily improved. However, existing stere...
arXiv Computer Vision
3d ago
PhasorNet: Learning Structure from Frequency for Real-Time Stereo Matching
arXiv:2608.29819v1 Announce Type: new Abstract: Accurate stereo matching remains challenging in ill-posed regions such as fine structures, reflective, or transparent objects, where appearance cues ar...
arXiv AI
2d ago
HiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives
HiLRP introduces a unified attribution framework for Vision Transformers (ViTs) that addresses the challenges posed by diverse architectural designs. By decomposing ViT operations into four basic types—linear maps, bilinear mixing, normalization/gating, and reindexing—HiLRP applies conservation‑satisfying relevance rules, enabling reliable explanations across a wide range of backbones. The method outperforms 14 existing attribution techniques on 10 architectures, maintaining conservation and improving localization accuracy (0.97 Pointing) compared to competitors.
arXiv Machine Learning
Jul 7
SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers
arXiv:2607. 03612v1 Announce Type: cross Abstract: Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success.
arXiv Computer Vision
Aug 24
Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection
Crane is a CLIP‑based framework for zero‑shot anomaly detection that enhances dense localization by adapting the vision encoder with a correlation‑based attention module and conditioning learnable prompts on global image context. It further fuses anomaly‑relevant patch features into the global representation for more sensitive image‑level detection, and a variant called Crane+ leverages DINOv2 spatial correlations for stronger pixel‑level performance. Across seven industrial benchmarks, Crane raises mean image‑level AP by 4.5% and Crane+ boosts mean pixel‑level AUPRO by 9.0%.