SyncAI.news, a Varaisys broadcasting
UltraMatch: Transport Path Routing for Ultra-Fast and Memory-Efficient Image Matching
JL

Jiajun Le, Yifan Lu, Zizhuo Li, Lei Cao, Junjun Jiang, Jiayi Ma

· 1 min read

ResearcharXiv cs.CV

UltraMatch: Transport Path Routing for Ultra-Fast and Memory-Efficient Image Matching

arXiv:2609.36980v1 Announce Type: new Abstract: Despite recent advances in accuracy and efficiency, coarse matching remains an indispensable yet costly stage in existing semi-dense matchers due to dense token-level matching. We present UltraMatch, an ultra-efficient and scalable semi-dense matching framework that bypasses the quadratic computation and memory cost of dense token-level matching by routing only a small fraction of candidate matching paths. At its core, a lightweight Transport Path Router operates on coarse block representations to rank candidate target blocks for each source block and retain only a small set, restricting subsequent token-level matching to the selected paths and avoiding the construction of the full token-to-token matching matrix. We further design a sparse global Dual-Softmax that performs matching only over the routed block candidates while retaining global competition across the sparse matching space. Beyond matching acceleration, UltraMatch employs deployment-oriented structural reparameterization for feature extraction and a tiny fine matching head with shared parameters, further reducing inference cost and memory consumption. UltraMatch achieves competitive accuracy among semi-dense matchers, while running 1.67$\times$ faster than SuperPoint+LightGlue with only 0.44 GiB peak inference memory. Its scalability enables inference at up to 6K resolution on a single RTX 3090, whereas existing semi-dense matchers run out of memory before reaching 2K. Our routing strategy is also transferable, delivering about 2$\times$ end-to-end speedup in EDM and ELoFTR without accuracy loss. The project repository is available at https://github.com/JiajunLe/UltraMatch.

Original source

This story was published by arXiv cs.CV and written by Jiajun Le, Yifan Lu, Zizhuo Li, Lei Cao, Junjun Jiang, Jiayi Ma. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News