Papers › Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence

Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence

19 Sep 2022arXiv:2209.08742archive 2025-07-28

Sunghwan Hong, Seokju Cho, Seungryong Kim, Stephen Lin

We present a novel architecture for dense correspondence. The current state-of-the-art are Transformer-based approaches that focus on either feature descriptors or cost volume aggregation. However, they generally aggregate one or the other but not both, though joint aggregation would boost each other by providing information that one has but other lacks, i.e., structural or semantic information of an image, or pixel-wise matching similarity. In this work, we propose a novel Transformer-based network that interleaves both forms of aggregations in a way that exploits their complementary information. Specifically, we design a self-attention layer that leverages the descriptor to disambiguate the noisy cost volume and that also utilizes the cost volume to aggregate features in a manner that promotes accurate matching. A subsequent cross-attention layer performs further aggregation conditioned on the descriptors of both images and aided by the aggregated outputs of earlier layers. We further boost the performance with hierarchical processing, in which coarser level aggregations guide those at finer levels. We evaluate the effectiveness of the proposed method on dense matching tasks and achieve state-of-the-art performance on all the major benchmarks. Extensive ablation studies are also provided to validate our design choices.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Geometric MatchingSemantic correspondence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Geometric Matching HPatches IFCAT (Ours) Average End-Point Error 17.59 #1 of 1 Archive leaderboard report
Semantic correspondence SPair-71k IFCAT PCK 64.4 #8 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections