DeepAI AI Chat
Log In Sign Up

3D Shape Completion with Multi-view Consistent Inference

by   Tao Hu, et al.
University of Maryland

3D shape completion is important to enable machines to perceive the complete geometry of objects from partial observations. To address this problem, view-based methods have been presented. These methods represent shapes as multiple depth images, which can be back-projected to yield corresponding 3D point clouds, and they perform shape completion by learning to complete each depth image using neural networks. While view-based methods lead to state-of-the-art results, they currently do not enforce geometric consistency among the completed views during the inference stage. To resolve this issue, we propose a multi-view consistent inference technique for 3D shape completion, which we express as an energy minimization problem including a data term and a regularization term. We formulate the regularization term as a consistency loss that encourages geometric consistency among multiple views, while the data term guarantees that the optimized views do not drift away too much from a learned shape descriptor. Experimental results demonstrate that our method completes shapes more accurately than previous techniques.


page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8


Render4Completion: Synthesizing Multi-view Depth Maps for 3D Shape Completion

We propose a novel approach for 3D shape completion by synthesizing mult...

Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis

3D-aware image synthesis aims to generate images of objects from multipl...

Multiple View Performers for Shape Completion

We propose the Multiple View Performer (MVP) - a new architecture for 3D...

3D Shape Segmentation with Projective Convolutional Networks

This paper introduces a deep architecture for segmenting 3D objects into...

Part2Word: Learning Joint Embedding of Point Clouds and Text by Matching Parts to Words

It is important to learn joint embedding for 3D shapes and text in diffe...

Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment

Neural signed distance functions (SDFs) have shown remarkable capability...