Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction (SIGGRAPH 2020)
Thin structures, such as wire-frame sculptures, fences, cables, power lines, and tree branches, are common in the real world. It is extremely challenging to acquire their 3D digital models using traditional image-based or depth-based reconstruction methods because thin structures often lack distinct point features and have severe self-occlusion. We propose the first approach that simultaneously estimates camera motion and reconstructs the geometry of complex 3D thin structures in high quality from a color video captured by a handheld camera. Specifically, we present a new curve-based approach to estimate accurate camera poses by establishing correspondences between featureless thin objects in the foreground in consecutive video frames, without requiring visual texture in the background scene to lock on. Enabled by this effective curve-based camera pose estimation strategy, we develop an iterative optimization method with tailored measures on geometry, topology as well as self-occlusion handling for reconstructing 3D thin structures. Extensive validations on a variety of thin structures show that our method achieves accurate camera pose estimation and faithful reconstruction of 3D thin structures with complex shape and topology at a level that has not been attained by other existing reconstruction methods.
P. Wang, L. Liu, N. Chen, H-K. Chu, C. Theobalt and W. Wang, Vid2Curve: Simultaneously Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video, ACM Transactions on Graphics (Proc. of SIGGRAPH 2020)
Видео Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction (SIGGRAPH 2020) канала Christian Theobalt
P. Wang, L. Liu, N. Chen, H-K. Chu, C. Theobalt and W. Wang, Vid2Curve: Simultaneously Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video, ACM Transactions on Graphics (Proc. of SIGGRAPH 2020)
Видео Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction (SIGGRAPH 2020) канала Christian Theobalt
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
XNect: Real-time Multi-person 3D Motion Capture With a Single RGB Camera (SIGGRAPH 2020)Wave Curves: Simulating Lagrangian water waves on dynamically deforming surfaces (SIGGRAPH 2020)The Design Space of Plane Elastic Curves [SIGGRAPH 2021]High-Speed Focal Tracking Projection Based on Liquid LensMotion Estimation TechniquesNeural Sparse Voxel Fields (NeurIPS 2020)Immersive Light Field Video with a Layered Mesh RepresentationSIGGRAPH Asia 2018 – Technical Papers TrailerATLAS: End-to-End 3D Scene Reconstruction from Posed Images (ECCV 2020)Only web Cam. Real time motion capture. - 3D pose estimationSelf-supervised Face Model Learning for Monocular Reconstruction at 250 Hz (CVPR 2018 Oral)(SIGGRAPH 2020) IQ-MPM: An Interface Quadrature Material Point Method for Coupled Solids and FluidsCapturing Detailed Deformations of Moving Human Bodies | Siggraph 2021Water Surface Wavelets (SIGGRAPH 2018)Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data - CVPR 2020Homogenized Yarn-Level Cloth [SIGGRAPH 2020]i3DMM: Deep Implicit 3D Morphable Model of Human HeadsConsistent Video Depth EstimationNeural Holography | SIGGRAPH 2020 ETech - 15 min tech talk[SIGGRAPH 2020] RoboCut: Hot-wire Cutting with Robot-controlled Flexible Rods