Timezone: »

 
Poster
Learning Deformable Tetrahedral Meshes for 3D Reconstruction
Jun Gao · Wenzheng Chen · Tommy Xiang · Alec Jacobson · Morgan McGuire · Sanja Fidler

Wed Dec 09 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1295
in Poster Session 5 »

3D shape representations that accommodate learning-based 3D reconstruction are an open problem in machine learning and computer graphics. Previous work on neural 3D reconstruction demonstrated benefits, but also limitations, of point cloud, voxel, surface mesh, and implicit function representations. We introduce \emph{Deformable Tetrahedral Meshes} (DefTet) as a particular parameterization that utilizes volumetric tetrahedral meshes for the reconstruction problem. Unlike existing volumetric approaches, DefTet optimizes for both vertex placement and occupancy, and is differentiable with respect to standard 3D reconstruction loss functions. It is thus simultaneously high-precision, volumetric, and amenable to learning-based neural architectures. We show that it can represent arbitrary, complex topology, is both memory and computationally efficient, and can produce high-fidelity reconstructions with a significantly smaller grid size than alternative volumetric approaches. The predicted surfaces are also inherently defined as tetrahedral meshes, thus do not require post-processing. We demonstrate that DefTetmatches or exceeds both the quality of the previous best approaches and the performance of the fastest ones. Our approach obtains high-quality tetrahedral meshes computed directly from noisy point clouds, and is the first to showcase high-quality 3D results using only a single image as input.

Keywords: Applications -> Computer Vision; Deep Learning -> CNN Architectures · Applications -> Body Pose, Face, and Gesture Analysis

Author Information

Jun Gao (University of Toronto; Nvidia)
Wenzheng Chen (University of Toronto)
Tommy Xiang (University of Toronto)
Alec Jacobson (University of Toronto)
Morgan McGuire (NVIDIA)
Sanja Fidler (University of Toronto)

More from the Same Authors