{"url":"/task/rgb-d-salient-object-detection","name":"RGB-D Salient Object Detection","slug":"rgb-d-salient-object-detection","description_markdown":"RGB-D Salient object detection (SOD) aims at distinguishing the most visually distinctive objects or regions in a scene from the given RGB and Depth data. It has a wide range of applications, including video/image segmentation, object recognition, visual tracking, foreground maps evaluation, image retrieval, content-aware image editing, information discovery, photosynthesis, and weakly\r\nsupervised semantic segmentation. Here, depth information plays an important complementary role in finding salient objects. Online benchmark: http://dpfan.net/d3netbenchmark.\r\n\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks, TNNLS20](https://ieeexplore.ieee.org/abstract/document/9107477) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":88,"papers_with_code":61,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nju2k","slug":"rgb-d-salient-object-detection-on-nju2k","dataset":"NJU2K","dataset_url":"/dataset/nju2k","rows_in_archive":27,"metrics":["S-Measure","Average MAE","max E-Measure","max F-Measure"],"first_row_in_archive_order":{"model":"DFormer-L","paper_title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","paper_url":"/paper/dformer-rethinking-rgbd-representation","paper_date":"2023-09-18","arxiv_id":"2309.09668","code_links":[{"title":"VCIP-RGBD/DFormer","url":"https://github.com/VCIP-RGBD/DFormer"}],"syntology":null}},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-sip","slug":"rgb-d-salient-object-detection-on-sip","dataset":"SIP","dataset_url":"/dataset/sip","rows_in_archive":16,"metrics":["S-Measure","Average MAE","max E-Measure","max F-Measure"],"first_row_in_archive_order":{"model":"DFormer-L","paper_title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","paper_url":"/paper/dformer-rethinking-rgbd-representation","paper_date":"2023-09-18","arxiv_id":"2309.09668","code_links":[{"title":"VCIP-RGBD/DFormer","url":"https://github.com/VCIP-RGBD/DFormer"}],"syntology":null}},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nlpr","slug":"rgb-d-salient-object-detection-on-nlpr","dataset":"NLPR","dataset_url":"/dataset/nlpr","rows_in_archive":14,"metrics":["S-Measure","Average MAE","max E-Measure","max F-Measure"],"first_row_in_archive_order":{"model":"DFormer-L","paper_title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","paper_url":"/paper/dformer-rethinking-rgbd-representation","paper_date":"2023-09-18","arxiv_id":"2309.09668","code_links":[{"title":"VCIP-RGBD/DFormer","url":"https://github.com/VCIP-RGBD/DFormer"}],"syntology":null}},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-stere","slug":"rgb-d-salient-object-detection-on-stere","dataset":"STERE","dataset_url":null,"rows_in_archive":14,"metrics":["S-Measure","Average MAE","max E-Measure","max F-Measure"],"first_row_in_archive_order":{"model":"DFormer-L","paper_title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","paper_url":"/paper/dformer-rethinking-rgbd-representation","paper_date":"2023-09-18","arxiv_id":"2309.09668","code_links":[{"title":"VCIP-RGBD/DFormer","url":"https://github.com/VCIP-RGBD/DFormer"}],"syntology":null}},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-des","slug":"rgb-d-salient-object-detection-on-des","dataset":"DES","dataset_url":null,"rows_in_archive":13,"metrics":["S-Measure","Average MAE","max E-Measure","max F-Measure"],"first_row_in_archive_order":{"model":"DFormer-L","paper_title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","paper_url":"/paper/dformer-rethinking-rgbd-representation","paper_date":"2023-09-18","arxiv_id":"2309.09668","code_links":[{"title":"VCIP-RGBD/DFormer","url":"https://github.com/VCIP-RGBD/DFormer"}],"syntology":null}},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-lfsd","slug":"rgb-d-salient-object-detection-on-lfsd","dataset":"LFSD","dataset_url":"/dataset/lfsd","rows_in_archive":8,"metrics":["S-Measure","Average MAE","max E-Measure","max F-Measure"],"first_row_in_archive_order":{"model":"UCNet-CVAE","paper_title":"Uncertainty Inspired RGB-D Saliency Detection","paper_url":"/paper/uncertainty-inspired-rgb-d-saliency-detection","paper_date":"2020-09-07","arxiv_id":"2009.03075","code_links":[{"title":"taozh2017/RGBD-SODsurvey","url":"https://github.com/taozh2017/RGBD-SODsurvey"},{"title":"JingZhang617/UCNet","url":"https://github.com/JingZhang617/UCNet"},{"title":"DengPingFan/S-measure","url":"https://github.com/DengPingFan/S-measure"},{"title":"DengPingFan/SOC-DataAug","url":"https://github.com/DengPingFan/SOC-DataAug"}],"syntology":null}},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-ssd","slug":"rgb-d-salient-object-detection-on-ssd","dataset":"RGBD135","dataset_url":null,"rows_in_archive":5,"metrics":["Average MAE","S-Measure","max E-Measure","max F-Measure"],"first_row_in_archive_order":{"model":"DASNet","paper_title":"Is Depth Really Necessary for Salient Object Detection?","paper_url":"/paper/is-depth-really-necessary-for-salient-object","paper_date":"2020-05-30","arxiv_id":"2006.00269","code_links":[{"title":"JiaweiZhao-git/DASNet","url":"https://github.com/JiaweiZhao-git/DASNet"}],"syntology":null}},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-njud","slug":"rgb-d-salient-object-detection-on-njud","dataset":"NJUD","dataset_url":null,"rows_in_archive":1,"metrics":["S-Measure"],"first_row_in_archive_order":{"model":"VST","paper_title":"Visual Saliency Transformer","paper_url":"/paper/visual-saliency-transformer","paper_date":"2021-04-25","arxiv_id":"2104.12099","code_links":[{"title":"nnizhang/VST","url":"https://github.com/nnizhang/VST"},{"title":"fhshen2022/prunerepaint","url":"https://github.com/fhshen2022/prunerepaint"}],"syntology":{"n":11,"n_ran":7,"n_unverified":4,"n_pointer_only":11}}}],"datasets":[{"url":"/dataset/nlpr","name":"NLPR","full_name":"","num_papers_in_archive":113},{"url":"/dataset/lfsd","name":"LFSD","full_name":"Light Field Saliency Database","num_papers_in_archive":80},{"url":"/dataset/sip","name":"SIP","full_name":"Salient Person","num_papers_in_archive":61},{"url":"/dataset/nju2k","name":"NJU2K","full_name":"","num_papers_in_archive":52},{"url":"/dataset/redweb-s","name":"ReDWeb-S","full_name":null,"num_papers_in_archive":9}],"subtasks":[],"parent_tasks":[{"url":"/task/object-detection","name":"Object Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":61,"tagged_in_all":88,"items":[{"url":"/paper/rgb-d-salient-object-detection-a-survey","title":"RGB-D Salient Object Detection: A Survey","date":"2020-08-01","arxiv_id":"2008.00230","repositories_listed":9,"syntology":null},{"url":"/paper/uncertainty-inspired-rgb-d-saliency-detection","title":"Uncertainty Inspired RGB-D Saliency Detection","date":"2020-09-07","arxiv_id":"2009.03075","repositories_listed":4,"syntology":null},{"url":"/paper/cir-net-cross-modality-interaction-and","title":"CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection","date":"2022-10-06","arxiv_id":"2210.02843","repositories_listed":3,"syntology":null},{"url":"/paper/point-aware-interaction-and-cnn-induced","title":"Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detection","date":"2023-08-17","arxiv_id":"2308.08930","repositories_listed":2,"syntology":null},{"url":"/paper/visual-saliency-transformer","title":"Visual Saliency Transformer","date":"2021-04-25","arxiv_id":"2104.12099","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_unverified":4,"n_pointer_only":11}},{"url":"/paper/siamese-network-for-rgb-d-salient-object","title":"Siamese Network for RGB-D Salient Object Detection and Beyond","date":"2020-08-26","arxiv_id":"2008.12134","repositories_listed":2,"syntology":null},{"url":"/paper/accurate-rgb-d-salient-object-detection-via","title":"Accurate RGB-D Salient Object Detection via Collaborative Learning","date":"2020-07-23","arxiv_id":"2007.11782","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/cross-modal-weighting-network-for-rgb-d","title":"Cross-Modal Weighting Network for RGB-D Salient Object Detection","date":"2020-07-09","arxiv_id":"2007.04901","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/bbs-net-rgb-d-salient-object-detection-with-a","title":"Bifurcated backbone strategy for RGB-D salient object detection","date":"2020-07-06","arxiv_id":"2007.02713","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/rethinking-rgb-d-salient-object-detection","title":"Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks","date":"2019-07-15","arxiv_id":"1907.06781","repositories_listed":2,"syntology":null},{"url":"/paper/contrast-prior-and-fluid-pyramid-integration","title":"Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection","date":"2019-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/pdnet-prior-model-guided-depth-enhanced","title":"PDNet: Prior-model Guided Depth-enhanced Network for Salient Object Detection","date":"2018-03-23","arxiv_id":"1803.08636","repositories_listed":2,"syntology":null},{"url":"/paper/lightweight-rgb-d-salient-object-detection","title":"Lightweight RGB-D Salient Object Detection from a Speed-Accuracy Tradeoff Perspective","date":"2025-05-07","arxiv_id":"2505.04758","repositories_listed":1,"syntology":null},{"url":"/paper/dual-mutual-learning-network-with-global","title":"Dual Mutual Learning Network with Global-local Awareness for RGB-D Salient Object Detection","date":"2025-01-03","arxiv_id":"2501.01648","repositories_listed":1,"syntology":null},{"url":"/paper/mambasod-dual-mamba-driven-cross-modal-fusion","title":"MambaSOD: Dual Mamba-Driven Cross-Modal Fusion Network for RGB-D Salient Object Detection","date":"2024-10-19","arxiv_id":"2410.15015","repositories_listed":1,"syntology":null},{"url":"/paper/cola-conditional-dropout-and-language-driven","title":"CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection","date":"2024-07-09","arxiv_id":"2407.06780","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/dformer-rethinking-rgbd-representation","title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","date":"2023-09-18","arxiv_id":"2309.09668","repositories_listed":1,"syntology":null},{"url":"/paper/mutual-information-regularization-for-weakly","title":"Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection","date":"2023-06-06","arxiv_id":"2306.03630","repositories_listed":1,"syntology":null},{"url":"/paper/depth-quality-inspired-feature-manipulation-1","title":"Depth Quality-Inspired Feature Manipulation for Efficient RGB-D and Video Salient Object Detection","date":"2022-08-08","arxiv_id":"2208.03918","repositories_listed":1,"syntology":null},{"url":"/paper/spsn-superpixel-prototype-sampling-network","title":"SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection","date":"2022-07-16","arxiv_id":"2207.07898","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/tanet-transformer-based-asymmetric-network","title":"TANet: Transformer-based Asymmetric Network for RGB-D Salient Object Detection","date":"2022-07-04","arxiv_id":"2207.01172","repositories_listed":1,"syntology":null},{"url":"/paper/promoting-saliency-from-depth-deep-1","title":"Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection","date":"2022-05-15","arxiv_id":"2205.07179","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/an-energy-based-prior-for-generative-saliency","title":"An Energy-Based Prior for Generative Saliency","date":"2022-04-19","arxiv_id":"2204.08803","repositories_listed":1,"syntology":null},{"url":"/paper/joint-learning-of-salient-object-detection","title":"Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction","date":"2022-03-09","arxiv_id":"2203.04895","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/boosting-rgb-d-saliency-detection-by","title":"Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images","date":"2022-01-01","arxiv_id":"2201.00100","repositories_listed":1,"syntology":null},{"url":"/paper/transcmd-cross-modal-decoder-equipped-with","title":"CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection","date":"2021-12-04","arxiv_id":"2112.02363","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/mtfnet-mutual-transformer-fusion-network-for","title":"MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion Attention","date":"2021-12-02","arxiv_id":"2112.01177","repositories_listed":1,"syntology":null},{"url":"/paper/joint-semantic-mining-for-weakly-supervised","title":"Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tritransnet-rgb-d-salient-object-detection","title":"TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network","date":"2021-08-09","arxiv_id":"2108.03990","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/cross-modality-discrepant-interaction-network","title":"Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection","date":"2021-08-04","arxiv_id":"2108.01971","repositories_listed":1,"syntology":null}],"syntology_records":10,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}