{"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/roca-robust-cad-model-retrieval-and-alignment","title":"ROCA: Robust CAD Model Retrieval and Alignment from a Single Image","arxiv_id":"2112.01988","date":"2021-12-03","proceeding":"CVPR 2022 1","authors":["Can Gümeli","Angela Dai","Matthias Nießner"],"abstract":"We present ROCA, a novel end-to-end approach that retrieves and aligns 3D CAD models from a shape database to a single input image. This enables 3D perception of an observed scene from a 2D RGB observation, characterized as a lightweight, compact, clean CAD representation. Core to our approach is our differentiable alignment optimization based on dense 2D-3D object correspondences and Procrustes alignment. ROCA can thus provide a robust CAD alignment while simultaneously informing CAD retrieval by leveraging the 2D-3D correspondences to learn geometrically similar CAD models. Experiments on challenging, real-world imagery from ScanNet show that ROCA significantly improves on state of the art, from 9.5% to 17.6% in retrieval-aware CAD alignment accuracy.","url_abs":"https://arxiv.org/abs/2112.01988v2","url_pdf":"https://arxiv.org/pdf/2112.01988v2.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":"roca-robust-cad-model-retrieval-and-alignment","repo_url":"https://github.com/cangumeli/ROCA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-dense-shape-correspondence","task_name":"3D Dense Shape Correspondence"},{"task_slug":"3d-object-detection-from-monocular-images","task_name":"3D Object Detection From Monocular Images"},{"task_slug":"3d-object-retrieval","task_name":"3D Object Retrieval"},{"task_slug":"3d-shape-reconstruction-from-a-single-2d","task_name":"3D Shape Reconstruction From A Single 2D Image"}],"methods":[{"method_slug":"3d-convolution","method_name":"3D Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"procrustes","method_name":"Procrustes"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"triplet-loss","method_name":"Triplet Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.01988","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}