3D-PSRNet: Part Segmented 3D Point Cloud Reconstruction From a Single Image (2018-09-08T00:00:00.000000Z)

TL;DR

It is demonstrated that jointly training for both reconstruction and segmentation leads to improved performance in both the tasks, when compared to training for each task individually.

Abstract

We propose a mechanism to reconstruct part annotated 3D point clouds of objects given just a single input image. We demonstrate that jointly training for both reconstruction and segmentation leads to improved performance in both the tasks, when compared to training for each task individually. The key idea is to propagate information from each task so as to aid the other during the training procedure. Towards this end, we introduce a location-aware segmentation loss in the training regime. We empirically show the effectiveness of the proposed loss in generating more faithful part reconstructions while also improving segmentation accuracy. We thoroughly evaluate the proposed approach on different object categories from the ShapeNet dataset to obtain improved results in reconstruction as well as segmentation.

Authors

R. Venkatesh Babu

14 papers

Priyanka Mandikal

4 papers

L. NavaneetK.

3 papers

3D-PSRNet: Part Segmented 3D Point Cloud Reconstruction From a Single Image

TL;DR

Abstract

Authors

References25 items

PointCNN

3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

A Papier-Mache Approach to Learning 3D Surface Generation

PointCNN: Convolution On X-Transformed Points

MarrNet: 3D Shape Reconstruction via 2.5D Sketches

Evolutionary Constraints on Human Object Perception

Tags2Parts: Discovering Semantic Regions from Shape Tags

Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction from a Single Image

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Multi-view Supervision for Single-View Reconstruction via Differentiable Ray Consistency

Mask R-CNN

3D Shape Segmentation with Projective Convolutional Networks

A Point Set Generation Network for 3D Object Reconstruction from a Single Image

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision

Semantic Scene Completion from a Single Depth Image

A scalable active framework for region annotation in 3D shape collections

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction

Learning a Predictable and Generative Vector Representation for Objects

ShapeNet: An Information-Rich 3D Model Repository

Fully convolutional networks for semantic segmentation

Why New Programming Languages for Simulation?

Part Segmented

Field of Study