{"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/rethinking-rgb-d-salient-object-detection","title":"Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks","arxiv_id":"1907.06781","date":"2019-07-15","proceeding":null,"authors":["Deng-Ping Fan","Zheng Lin","Jia-Xing Zhao","Yun Liu","Zhao Zhang","Qibin Hou","Menglong Zhu","Ming-Ming Cheng"],"abstract":"The use of RGB-D information for salient object detection has been extensively explored in recent years. However, relatively few efforts have been put towards modeling salient object detection in real-world human activity scenes with RGBD. In this work, we fill the gap by making the following contributions to RGB-D salient object detection. (1) We carefully collect a new SIP (salient person) dataset, which consists of ~1K high-resolution images that cover diverse real-world scenes from various viewpoints, poses, occlusions, illuminations, and backgrounds. (2) We conduct a large-scale (and, so far, the most comprehensive) benchmark comparing contemporary methods, which has long been missing in the field and can serve as a baseline for future research. We systematically summarize 32 popular models and evaluate 18 parts of 32 models on seven datasets containing a total of about 97K images. (3) We propose a simple general architecture, called Deep Depth-Depurator Network (D3Net). It consists of a depth depurator unit (DDU) and a three-stream feature learning module (FLM), which performs low-quality depth map filtering and cross-modal feature learning respectively. These components form a nested structure and are elaborately designed to be learned jointly. D3Net exceeds the performance of any prior contenders across all five metrics under consideration, thus serving as a strong model to advance research in this field. We also demonstrate that D3Net can be used to efficiently extract salient object masks from real scenes, enabling effective background changing application with a speed of 65fps on a single GPU. All the saliency maps, our new SIP dataset, the D3Net model, and the evaluation tools are publicly available at https://github.com/DengPingFan/D3NetBenchmark.","url_abs":"https://arxiv.org/abs/1907.06781v2","url_pdf":"https://arxiv.org/pdf/1907.06781v2.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":"rethinking-rgb-d-salient-object-detection","repo_url":"https://github.com/DengPingFan/D3NetBenchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"rethinking-rgb-d-salient-object-detection","repo_url":"https://github.com/taozh2017/RGBD-SODsurvey","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"salient-object-detection","task_name":"RGB Salient Object Detection"},{"task_slug":"rgb-d-salient-object-detection","task_name":"RGB-D Salient Object Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[{"slug":"sip","name":"SIP","full_name":"Salient Person"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/rgb-d-salient-object-detection-on-lfsd","task":"RGB-D Salient Object Detection","dataset":"LFSD","model":"D3Net","rank_in_archive_order":7,"of":8,"metrics":{"Average MAE":"0.095","S-Measure":"82.5","max E-Measure":"86.2","max F-Measure":"81.0"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nju2k","task":"RGB-D Salient Object Detection","dataset":"NJU2K","model":"D3Net","rank_in_archive_order":15,"of":27,"metrics":{"Average MAE":"0.046","S-Measure":"90.0","max E-Measure":"93.9","max F-Measure":"90.0"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nlpr","task":"RGB-D Salient Object Detection","dataset":"NLPR","model":"D3Net","rank_in_archive_order":12,"of":14,"metrics":{"Average MAE":"0.030","S-Measure":"91.2","max E-Measure":"95.3","max F-Measure":"89.7"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-ssd","task":"RGB-D Salient Object Detection","dataset":"RGBD135","model":"D3Net","rank_in_archive_order":4,"of":5,"metrics":{"Average MAE":"0.058","S-Measure":"85.7","max E-Measure":"91.0","max F-Measure":"83.4"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-sip","task":"RGB-D Salient Object Detection","dataset":"SIP","model":"D3Net","rank_in_archive_order":14,"of":16,"metrics":{"Average MAE":"0.063","S-Measure":"86.0","max E-Measure":"90.9","max F-Measure":"86.1"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-stere","task":"RGB-D Salient Object Detection","dataset":"STERE","model":"D3Net","rank_in_archive_order":12,"of":14,"metrics":{"Average MAE":"0.046","S-Measure":"89.9","max E-Measure":"93.8","max F-Measure":"89.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1907.06781","atlas_url":"https://app.syntology.ai/?focus=1907.06781","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1907.06781"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1907.06781\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1907.06781"},"call":"get_concepts_for_paper(arxiv_id=\"1907.06781\")"}],"by_repo":[{"repo":"DengPingFan/D3NetBenchmark","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"taozh2017/RGBD-SODsurvey","kind":"listed","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":"1d1c08e3fe0e07492c5273f1e7b5e2c545d48d249dbacbdc41e7859e7042f710","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}