{"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/3d-physnet-learning-the-intuitive-physics-of","title":"3D-PhysNet: Learning the Intuitive Physics of Non-Rigid Object Deformations","arxiv_id":"1805.00328","date":"2018-04-25","proceeding":null,"authors":["Zhihua Wang","Stefano Rosa","Bo Yang","Sen Wang","Niki Trigoni","Andrew Markham"],"abstract":"The ability to interact and understand the environment is a fundamental\nprerequisite for a wide range of applications from robotics to augmented\nreality. In particular, predicting how deformable objects will react to applied\nforces in real time is a significant challenge. This is further confounded by\nthe fact that shape information about encountered objects in the real world is\noften impaired by occlusions, noise and missing regions e.g. a robot\nmanipulating an object will only be able to observe a partial view of the\nentire solid. In this work we present a framework, 3D-PhysNet, which is able to\npredict how a three-dimensional solid will deform under an applied force using\nintuitive physics modelling. In particular, we propose a new method to encode\nthe physical properties of the material and the applied force, enabling\ngeneralisation over materials. The key is to combine deep variational\nautoencoders with adversarial training, conditioned on the applied force and\nthe material properties. We further propose a cascaded architecture that takes\na single 2.5D depth view of the object and predicts its deformation. Training\ndata is provided by a physics simulator. The network is fast enough to be used\nin real-time applications from partial views. Experimental results show the\nviability and the generalisation properties of the proposed architecture.","url_abs":"http://arxiv.org/abs/1805.00328v2","url_pdf":"http://arxiv.org/pdf/1805.00328v2.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":"3d-physnet-learning-the-intuitive-physics-of","repo_url":"https://github.com/vividda/3D-PhysNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.00328","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}