Single Image 3D Object Estimation with Primitive Graph Networks

TL;DR

This paper introduces a primitive graph network approach for reconstructing 3D objects from a single image, effectively capturing global shape context and improving coherence in 3D reconstructions.

Contribution

It proposes a novel two-stage graph network framework that combines primitive proposal and reasoning modules for better 3D object estimation from images.

Findings

Outperforms previous methods on Pix3D, ModelNet, and NYU Depth V2 benchmarks.

Effectively captures global shape context and semantic constraints.

Produces more coherent 3D structures under challenging conditions.

Abstract

Reconstructing 3D object from a single image (RGB or depth) is a fundamental problem in visual scene understanding and yet remains challenging due to its ill-posed nature and complexity in real-world scenes. To address those challenges, we adopt a primitive-based representation for 3D object, and propose a two-stage graph network for primitive-based 3D object estimation, which consists of a sequential proposal module and a graph reasoning module. Given a 2D image, our proposal module first generates a sequence of 3D primitives from input image with local feature attention. Then the graph reasoning module performs joint reasoning on a primitive graph to capture the global shape context for each primitive. Such a framework is capable of taking into account rich geometry and semantic constraints during 3D structure recovery, producing 3D objects with more coherent structure even under challenging viewing conditions. We train the entire graph neural network in a stage-wise strategy and evaluate it on three benchmarks: Pix3D, ModelNet and NYU Depth V2. Extensive experiments show that our approach outperforms the previous state of the arts with a considerable margin.