{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dformerv2-geometry-self-attention-for-rgbd","title":"DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation","arxiv_id":"2504.04701","date":"2025-04-07","proceeding":"CVPR 2025 1","authors":["Bo-Wen Yin","Jiao-Long Cao","Ming-Ming Cheng","Qibin Hou"],"abstract":"Recent advances in scene understanding benefit a lot from depth maps because of the 3D geometry information, especially in complex conditions (e.g., low light and overexposed). Existing approaches encode depth maps along with RGB images and perform feature fusion between them to enable more robust predictions. Taking into account that depth can be regarded as a geometry supplement for RGB images, a straightforward question arises: Do we really need to explicitly encode depth information with neural networks as done for RGB images? Based on this insight, in this paper, we investigate a new way to learn RGBD feature representations and present DFormerv2, a strong RGBD encoder that explicitly uses depth maps as geometry priors rather than encoding depth information with neural networks. Our goal is to extract the geometry clues from the depth and spatial distances among all the image patch tokens, which will then be used as geometry priors to allocate attention weights in self-attention. Extensive experiments demonstrate that DFormerv2 exhibits exceptional performance in various RGBD semantic segmentation benchmarks. Code is available at: https://github.com/VCIP-RGBD/DFormer.","url_abs":"https://arxiv.org/abs/2504.04701v1","url_pdf":"https://arxiv.org/pdf/2504.04701v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dformerv2-geometry-self-attention-for-rgbd","repo_url":"https://github.com/VCIP-RGBD/DFormer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-geometry","task_name":"3D geometry"},{"task_slug":null,"task_name":"RGBD Semantic Segmentation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"DFormerv2-L","rank_in_archive_order":10,"of":121,"metrics":{"Mean IoU":"58.4%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"DFormerv2-B","rank_in_archive_order":15,"of":121,"metrics":{"Mean IoU":"57.7%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"DFormerv2-S","rank_in_archive_order":23,"of":121,"metrics":{"Mean IoU":"56.0%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"DFormerv2-L","rank_in_archive_order":5,"of":44,"metrics":{"Mean IoU":"53.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"DFormerv2-B","rank_in_archive_order":8,"of":44,"metrics":{"Mean IoU":"52.8%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"DFormerv2-S","rank_in_archive_order":13,"of":44,"metrics":{"Mean IoU":"51.5%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2504.04701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04701"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/VCIP-RGBD/DFormer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4e855a7a7f059a4a","entry":"build_backbone","repo":"VCIP-RGBD/DFormer","repo_kind":"official","path":"models/builder.py","file_url":"https://github.com/VCIP-RGBD/DFormer/blob/HEAD/models/builder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e855a7a7f059a4a"}},{"code_sha256_prefix":"4aff21eb03dec073","entry":"build_head","repo":"VCIP-RGBD/DFormer","repo_kind":"official","path":"models/builder.py","file_url":"https://github.com/VCIP-RGBD/DFormer/blob/HEAD/models/builder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4aff21eb03dec073"}},{"code_sha256_prefix":"4da122d79dc0e380","entry":"build_neck","repo":"VCIP-RGBD/DFormer","repo_kind":"official","path":"models/builder.py","file_url":"https://github.com/VCIP-RGBD/DFormer/blob/HEAD/models/builder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4da122d79dc0e380"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}