{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/iam-enhancing-rgb-d-instance-segmentation","title":"IAM: Enhancing RGB-D Instance Segmentation with New Benchmarks","arxiv_id":"2501.01685","date":"2025-01-03","proceeding":null,"authors":["Aecheon Jung","Soyun Choi","Junhong Min","Sungeun Hong"],"abstract":"Image segmentation is a vital task for providing human assistance and enhancing autonomy in our daily lives. In particular, RGB-D segmentation-leveraging both visual and depth cues-has attracted increasing attention as it promises richer scene understanding than RGB-only methods. However, most existing efforts have primarily focused on semantic segmentation and thus leave a critical gap. There is a relative scarcity of instance-level RGB-D segmentation datasets, which restricts current methods to broad category distinctions rather than fully capturing the fine-grained details required for recognizing individual objects. To bridge this gap, we introduce three RGB-D instance segmentation benchmarks, distinguished at the instance level. These datasets are versatile, supporting a wide range of applications from indoor navigation to robotic manipulation. In addition, we present an extensive evaluation of various baseline models on these benchmarks. This comprehensive analysis identifies both their strengths and shortcomings, guiding future work toward more robust, generalizable solutions. Finally, we propose a simple yet effective method for RGB-D data integration. Extensive evaluations affirm the effectiveness of our approach, offering a robust framework for advancing toward more nuanced scene understanding.","url_abs":"https://arxiv.org/abs/2501.01685v1","url_pdf":"https://arxiv.org/pdf/2501.01685v1.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":"iam-enhancing-rgb-d-instance-segmentation","repo_url":"https://github.com/aim-skku/box-is","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"iam-enhancing-rgb-d-instance-segmentation","repo_url":"https://github.com/aim-skku/nyudv2-is","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"iam-enhancing-rgb-d-instance-segmentation","repo_url":"https://github.com/aim-skku/sun-rgbd-is","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"data-integration","task_name":"Data Integration"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"rgb-d-instance-segmentation","task_name":"RGB-D Instance Segmentation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"box-is","name":"Box-IS","full_name":"Box-IS"},{"slug":"nyudv2-is","name":"NYUDv2-IS","full_name":""},{"slug":"sun-rgbd-is","name":"SUN-RGBD-IS","full_name":"SUN-RGBD-IS"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/instance-segmentation-on-box-is","task":"Instance Segmentation","dataset":"Box-IS","model":"IAM + SOLQ","rank_in_archive_order":1,"of":1,"metrics":{"mask AP":"83.7"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-nyudv2-is","task":"Instance Segmentation","dataset":"NYUDv2-IS","model":"IAM + SOLQ","rank_in_archive_order":1,"of":2,"metrics":{"mask AP":"35.8"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-nyudv2-is","task":"Instance Segmentation","dataset":"NYUDv2-IS","model":"IAM + DETR","rank_in_archive_order":2,"of":2,"metrics":{"mask AP":"32.3"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-sun-rgbd-is","task":"Instance Segmentation","dataset":"SUN-RGBD-IS","model":"IAM + SOLQ","rank_in_archive_order":1,"of":2,"metrics":{"mask AP":"25.7"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-sun-rgbd-is","task":"Instance Segmentation","dataset":"SUN-RGBD-IS","model":"IAM + DETR","rank_in_archive_order":2,"of":2,"metrics":{"mask AP":"22.9"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-instance-segmentation-on-box-is","task":"RGB-D Instance Segmentation","dataset":"Box-IS","model":"IAM + SOLQ","rank_in_archive_order":1,"of":1,"metrics":{"mask AP":"83.7"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-instance-segmentation-on-nyudv2-is","task":"RGB-D Instance Segmentation","dataset":"NYUDv2-IS","model":"IAM + SOLQ","rank_in_archive_order":1,"of":2,"metrics":{"mask AP":"35.8"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-instance-segmentation-on-nyudv2-is","task":"RGB-D Instance Segmentation","dataset":"NYUDv2-IS","model":"IAM + DETR","rank_in_archive_order":2,"of":2,"metrics":{"mask AP":"32.3"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-instance-segmentation-on-sun-rgbd-is","task":"RGB-D Instance Segmentation","dataset":"SUN-RGBD-IS","model":"IAM + SOLQ","rank_in_archive_order":1,"of":2,"metrics":{"mask AP":"25.7"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-instance-segmentation-on-sun-rgbd-is","task":"RGB-D Instance Segmentation","dataset":"SUN-RGBD-IS","model":"IAM + DETR","rank_in_archive_order":2,"of":2,"metrics":{"mask AP":"22.9"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"aim-skku/box-is","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"aim-skku/nyudv2-is","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"aim-skku/sun-rgbd-is","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b65e61c217f2f2f00f9f3ade4292efcfadbeaf448ef58986b4befb7a4699aee3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}