CVAug 20, 2019

Probabilistic Reconstruction Networks for 3D Shape Inference from a Single Image

arXiv:1908.07475v113 citations
AI Analysis

This addresses the problem of accurate 3D reconstruction from limited image data for applications in computer vision and graphics, representing an incremental advance with a more principled probabilistic approach.

The paper tackles 3D shape inference from a single image by proposing Probabilistic Reconstruction Networks, a probabilistic framework that decouples shape representation from inference and allows training with Monte Carlo or variational methods, achieving state-of-the-art results on ShapeNet with improvements in intersection over union and earth mover's distance metrics using a basic voxel grid representation.

We study end-to-end learning strategies for 3D shape inference from images, in particular from a single image. Several approaches in this direction have been investigated that explore different shape representations and suitable learning architectures. We focus instead on the underlying probabilistic mechanisms involved and contribute a more principled probabilistic inference-based reconstruction framework, which we coin Probabilistic Reconstruction Networks. This framework expresses image conditioned 3D shape inference through a family of latent variable models, and naturally decouples the choice of shape representations from the inference itself. Moreover, it suggests different options for the image conditioning and allows training in two regimes, using either Monte Carlo or variational approximation of the marginal likelihood. Using our Probabilistic Reconstruction Networks we obtain single image 3D reconstruction results that set a new state of the art on the ShapeNet dataset in terms of the intersection over union and earth mover's distance evaluation metrics. Interestingly, we obtain these results using a basic voxel grid representation, improving over recent work based on finer point cloud or mesh based representations.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes