PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories

06/10/2022
by   Yuchen Rao, et al.
5

While 3D shape representations enable powerful reasoning in many visual and perception applications, learning 3D shape priors tends to be constrained to the specific categories trained on, leading to an inefficient learning process, particularly for general applications with unseen categories. Thus, we propose PatchComplete, which learns effective shape priors based on multi-resolution local patches, which are often more general than full shapes (e.g., chairs and tables often both share legs) and thus enable geometric reasoning about unseen class categories. To learn these shared substructures, we learn multi-resolution patch priors across all train categories, which are then associated to input partial shape observations by attention across the patch priors, and finally decoded into a complete shape reconstruction. Such patch-based priors avoid overfitting to specific train categories and enable reconstruction on entirely unseen categories at test time. We demonstrate the effectiveness of our approach on synthetic ShapeNet data as well as challenging real-scanned objects from ScanNet, which include noise and clutter, improving over state of the art in novel-category shape completion by 19.3 distance on ShapeNet, and 9.0

READ FULL TEXT

page 16

page 18

page 19

research
08/04/2020

PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations

Implicit surface representations, such as signed-distance functions, com...
research
07/24/2022

PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation

This paper introduces a data-driven shape completion approach that focus...
research
09/20/2017

Learning quadrangulated patches for 3D shape parameterization and completion

We propose a novel 3D shape parameterization by surface patches, that ar...
research
12/14/2020

Deep Optimized Priors for 3D Shape Modeling and Reconstruction

Many learning-based approaches have difficulty scaling to unseen data, a...
research
01/12/2017

Surface Reconstruction with Data-driven Exemplar Priors

In this paper, we propose a framework to reconstruct 3D models from raw ...
research
01/06/2020

Meshlet Priors for 3D Mesh Reconstruction

Estimating a mesh from an unordered set of sparse, noisy 3D points is a ...
research
02/16/2020

Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories

We address the problem of discovering 3D parts for objects in unseen cat...

Please sign up or login with your details

Forgot password? Click here to reset