ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer
By Hongkai Chen, Zixin Luo, Lei Zhou, Yurun Tian, Mingmin Zhen, Tian Fang, David N. R. McKinnon, Yanghai Tsin, Long Quan. European Conference on Computer Vision, 2022
301 citations recorded by the source corpus.
Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher that is built on hierarchical attention structure, adopting a novel attention operation which is capable of adjusting attention span in a self-adaptive manner. To achieve this goal, first, flow maps are regressed in each cross attention phase to locate the center of search region. Next, a sampling grid is generated around the center, whose size, instead of being empirically configured as fixed, is adaptively computed from a pixel uncertainty estimated along with the flow map. Finally, attention is computed across two images within derived regions, referred to as attention span. By these means, we are able to not only maintain long-range dependencies, but also enable fine-grained attention among pixels of high relevance that compensates essential locality and piece-wise smoothness in matching tasks. State-of-the-art accuracy on a wide range of evaluation benchmarks validates the strong matching capability of our method.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/ff59e36f93640ac722ff81e3be92273df6ca7ef2
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
- Yohann Cabon
- Vincent Leroy
- Jérôme Revaud
- Luc Van Gool
- Cordelia Schmid
- Andrea Vedaldi
- Ming-Hsuan Yang
- Andreas Geiger
Citations in the corpus
- RoMa: Robust Dense Feature Matching (2023, unknown): “SotA comparison on Megadepth-8-Scenes [17].”
- Grounding Image Matching in 3D with MASt3R (2024, result): “In contrast to keypoint-based approaches, semi-dense [11,16,43,46,82,85] and dense approaches [27,28,29,58,92,93,94,122] offer a different paradigm for establishing image correspondences, considering all possible pixel associations.”
- DUSt3R: Geometric 3D Vision Made Easy (2023, unknown): “These improvements encompass advanced feature description [26, 28, 97, 135, 167], more accurate image matching [3, 17, 60, 82, 100, 120, 126, 145], featuremetric refinement [59], and neural bundle adjustment [58, 153].”