DeepAI AI Chat
Log In Sign Up

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

by   Tao Hu, et al.
University of Maryland

We propose a novel approach for 3D shape completion by synthesizing multi-view depth maps. While previous work for shape completion relies on volumetric representations, meshes, or point clouds, we propose to use multi-view depth maps from a set of fixed viewing angles as our shape representation. This allows us to be free of the limitations of memory for volumetric representations and point clouds by casting shape completion into an image-to-image translation problem. Specifically, we render depth maps of the incomplete shape from a fixed set of viewpoints, and perform depth map completion in each view. Different from image-to-image translation network that completes each view separately, our novel network, multi-view completion net (MVCN), leverages information from all views of a 3D shape to help the completion of each single view. This enables MVCN to leverage more information from different depth views to achieve high accuracy in single depth view completion and keep the consistency among the completed depth images in different views. Benefited by the multi-view representation and the novel network structure, MVCN significantly improves the accuracy of 3D shape completion in large-scale benchmarks compared to the state of the art.


page 5

page 6

page 7

page 8


3D Shape Completion with Multi-view Consistent Inference

3D shape completion is important to enable machines to perceive the comp...

Improved Modeling of 3D Shapes with Multi-view Depth Maps

We present a simple yet effective general-purpose framework for modeling...

Multiple View Performers for Shape Completion

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

MV-Map: Offboard HD-Map Generation with Multi-view Consistency

While bird's-eye-view (BEV) perception models can be useful for building...

RGBD-Net: Predicting color and depth images for novel views synthesis

We address the problem of novel view synthesis from an unstructured set ...

SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networks

Estimating a dense depth map from a single view is geometrically ill-pos...