{"id":32739,"date":"2026-01-21T17:02:33","date_gmt":"2026-01-21T17:02:33","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/efficient-multi-object-pose-estimation-using-multi-resolution-deformable-attention-and-query-aggregation\/"},"modified":"2026-09-17T11:25:53","modified_gmt":"2026-09-17T11:25:53","slug":"efficient-multi-object-pose-estimation-using-multi-resolution-deformable-attention-and-query-aggregation","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/efficient-multi-object-pose-estimation-using-multi-resolution-deformable-attention-and-query-aggregation\/","title":{"rendered":"Efficient Multi-Object Pose Estimation using Multi-Resolution Deformable Attention and Query Aggregation"},"content":{"rendered":"<p>Object pose estimation is a long-standing problem in computer vision. Recently, attention-based vision transformer models have achieved state-of-the-art results in many computer vision applications. Exploiting the permutation-invariant nature of the attention mechanism, a family of vision transformer models formulate multi-object pose estimation as a set prediction problem. However, existing vision transformer models for multi-object pose estimation rely exclusively on the attention mechanism. Convolutional neural networks, on the other hand, hard-wire various inductive biases into their architecture. In this paper, we investigate incorporating inductive biases in vision transformer models for multi-object pose estimation, which facilitates learning long-range dependencies while circumventing the costly global attention. In particular, we use multi-resolution deformable attention, where the attention operation is performed only between a few deformed reference points. Furthermore, we propose a query aggregation mechanism that enables increasing the number of object queries without increasing the computational complexity. We evaluate the proposed model on the challenging YCB-Video dataset and report state-of-the-art results.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Object pose estimation is a long-standing problem in computer vision. Recently, attention-based vision transformer models have achieved state-of-the-art results in many computer vision applications. Exploiting the permutation-invariant nature of the attention mechanism, a family of vision transformer models formulate multi-object pose estimation as a set prediction problem. However, existing vision transformer models for multi-object pose estimation rely exclusively on the attention mechanism. Convolutional neural networks, on the other hand, hard-wire [&hellip;]<\/p>\n","protected":false},"author":14,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[32],"class_list":["post-32739","publication","type-publication","status-publish","hentry","publication-type-inproceedings"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32739","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/14"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32739\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=32739"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=32739"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}