{"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/unsupervised-learning-of-category-level-3d-1","title":"Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos","arxiv_id":"2407.04384","date":"2024-07-05","proceeding":"CVPR 2024 1","authors":["Leonhard Sommer","Artur Jesslen","Eddy Ilg","Adam Kortylewski"],"abstract":"Category-level 3D pose estimation is a fundamentally important problem in computer vision and robotics, e.g. for embodied agents or to train 3D generative models. However, so far methods that estimate the category-level object pose require either large amounts of human annotations, CAD models or input from RGB-D sensors. In contrast, we tackle the problem of learning to estimate the category-level 3D pose only from casually taken object-centric videos without human supervision. We propose a two-step pipeline: First, we introduce a multi-view alignment procedure that determines canonical camera poses across videos with a novel and robust cyclic distance formulation for geometric and appearance matching using reconstructed coarse meshes and DINOv2 features. In a second step, the canonical poses and reconstructed meshes enable us to train a model for 3D pose estimation from a single image. In particular, our model learns to estimate dense correspondences between images and a prototypical 3D template by predicting, for each pixel in a 2D image, a feature vector of the corresponding vertex in the template mesh. We demonstrate that our method outperforms all baselines at the unsupervised alignment of object-centric videos by a large margin and provides faithful and robust predictions in-the-wild. Our code and data is available at https://github.com/GenIntel/uns-obj-pose3d.","url_abs":"https://arxiv.org/abs/2407.04384v1","url_pdf":"https://arxiv.org/pdf/2407.04384v1.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":"unsupervised-learning-of-category-level-3d-1","repo_url":"https://github.com/genintel/uns-obj-pose3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.04384","atlas_url":"https://app.syntology.ai/?focus=2407.04384","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}