{"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/3dvnet-multi-view-depth-prediction-and","title":"3DVNet: Multi-View Depth Prediction and Volumetric Refinement","arxiv_id":"2112.00202","date":"2021-12-01","proceeding":null,"authors":["Alexander Rich","Noah Stier","Pradeep Sen","Tobias Höllerer"],"abstract":"We present 3DVNet, a novel multi-view stereo (MVS) depth-prediction method that combines the advantages of previous depth-based and volumetric MVS approaches. Our key idea is the use of a 3D scene-modeling network that iteratively updates a set of coarse depth predictions, resulting in highly accurate predictions which agree on the underlying scene geometry. Unlike existing depth-prediction techniques, our method uses a volumetric 3D convolutional neural network (CNN) that operates in world space on all depth maps jointly. The network can therefore learn meaningful scene-level priors. Furthermore, unlike existing volumetric MVS techniques, our 3D CNN operates on a feature-augmented point cloud, allowing for effective aggregation of multi-view information and flexible iterative refinement of depth maps. Experimental results show our method exceeds state-of-the-art accuracy in both depth prediction and 3D reconstruction metrics on the ScanNet dataset, as well as a selection of scenes from the TUM-RGBD and ICL-NUIM datasets. This shows that our method is both effective and generalizes to new settings.","url_abs":"https://arxiv.org/abs/2112.00202v1","url_pdf":"https://arxiv.org/pdf/2112.00202v1.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":"3dvnet-multi-view-depth-prediction-and","repo_url":"https://github.com/alexrich021/3dvnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-human-action-recognition","task_name":"3D Action Recognition"},{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[{"method_slug":"3d-cnn","method_name":"3D CNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-action-recognition-on-ntu-rgb-d-1","task":"3D Action Recognition","dataset":"NTU RGB+D","model":"3DV-PointNet++","rank_in_archive_order":5,"of":5,"metrics":{"Cross Subject Accuracy":"88.8","Cross View Accuracy":"96.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.00202","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}