{"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/robust-rgb-d-fusion-for-saliency-detection","title":"Robust RGB-D Fusion for Saliency Detection","arxiv_id":"2208.01762","date":"2022-08-02","proceeding":null,"authors":["Zongwei Wu","Shriarulmozhivarman Gobichettipalayam","Brahim Tamadazte","Guillaume Allibert","Danda Pani Paudel","Cédric Demonceaux"],"abstract":"Efficiently exploiting multi-modal inputs for accurate RGB-D saliency detection is a topic of high interest. Most existing works leverage cross-modal interactions to fuse the two streams of RGB-D for intermediate features' enhancement. In this process, a practical aspect of the low quality of the available depths has not been fully considered yet. In this work, we aim for RGB-D saliency detection that is robust to the low-quality depths which primarily appear in two forms: inaccuracy due to noise and the misalignment to RGB. To this end, we propose a robust RGB-D fusion method that benefits from (1) layer-wise, and (2) trident spatial, attention mechanisms. On the one hand, layer-wise attention (LWA) learns the trade-off between early and late fusion of RGB and depth features, depending upon the depth accuracy. On the other hand, trident spatial attention (TSA) aggregates the features from a wider spatial context to address the depth misalignment problem. The proposed LWA and TSA mechanisms allow us to efficiently exploit the multi-modal inputs for saliency detection while being robust against low-quality depths. Our experiments on five benchmark datasets demonstrate that the proposed fusion method performs consistently better than the state-of-the-art fusion alternatives.","url_abs":"https://arxiv.org/abs/2208.01762v2","url_pdf":"https://arxiv.org/pdf/2208.01762v2.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":"robust-rgb-d-fusion-for-saliency-detection","repo_url":"https://github.com/zongwei97/rfnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"saliency-detection","task_name":"Saliency Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.01762","atlas_url":"https://app.syntology.ai/?focus=2208.01762","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}