eprintid: 10194974 rev_number: 6 eprint_status: archive userid: 699 dir: disk0/10/19/49/74 datestamp: 2024-07-23 14:42:29 lastmod: 2024-07-23 14:42:29 status_changed: 2024-07-23 14:42:29 type: proceedings_section metadata_visibility: show sword_depositor: 699 creators_name: Mohamed, M creators_name: Agapito, L title: DynamicSurf: Dynamic Neural RGB-D Surface Reconstruction With an Optimizable Feature Grid ispublished: pub divisions: UCL divisions: B04 divisions: F48 keywords: Geometry, Surface reconstruction, Solid modeling, Three-dimensional displays, Deformation,Network topology, Dynamics note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: We propose DynamicSurf, a model-free neural implicit surface reconstruction method for high-fidelity 3D modelling of non-rigid surfaces from monocular RGB-D video. To cope with the lack of multi-view cues in monocular sequences of deforming surfaces, one of the most challenging settings for 3D reconstruction, DynamicSurf exploits depth, surface normals, and RGB losses to improve reconstruction fidelity and optimisation time. DynamicSurf learns a neural deformation field that maps a canonical representation of the surface geometry to the current frame. We depart from current neural non-rigid surface reconstruction models by designing the canonical representation as a learned feature grid which leads to faster and more accurate surface reconstruction than competing approaches that use a single MLP. We demonstrate DynamicSurf on public datasets and show that it can optimize sequences of varying frames with 6× speedup over pure MLP-based approaches while achieving comparable results to the state-of-the-art methods. date: 2024-06-12 date_type: published publisher: IEEE official_url: http://dx.doi.org/10.1109/3dv62453.2024.00046 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2291888 doi: 10.1109/3DV62453.2024.00046 lyricists_name: De Agapito Vicente, Lourdes lyricists_id: LDEAG40 actors_name: De Agapito Vicente, Lourdes actors_id: LDEAG40 actors_role: owner full_text_status: public pres_type: paper publication: Proceedings - 2024 International Conference on 3D Vision, 3DV 2024 place_of_pub: Davos, Switzerland pagerange: 820-830 event_title: 2024 International Conference on 3D Vision (3DV) event_dates: 18 Mar 2024 - 21 Mar 2024 issn: 2475-7888 book_title: 2024 International Conference on 3D Vision (3DV) citation: Mohamed, M; Agapito, L; (2024) DynamicSurf: Dynamic Neural RGB-D Surface Reconstruction With an Optimizable Feature Grid. In: 2024 International Conference on 3D Vision (3DV). (pp. pp. 820-830). IEEE: Davos, Switzerland. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10194974/1/dynamicsurf.pdf