TopoNet: Topology Learning for 3D Reconstruction of Objects of Arbitrary Genus
- 25 March 2022
- journal article
- research article
- Published by Wiley in Computer Graphics Forum
- Vol. 41 (6) , 336-347
Abstract
We propose a deep reinforcement learning‐based solution for the 3D reconstruction of objects of complex topologies from a single RGB image. We use a template‐based approach. However, unlike previous template‐based methods, which are limited to the reconstruction of 3D objects of fixed topology, our approach learns simultaneously the geometry and topology of the target 3D shape in the input image. To this end, we propose a neural network that learns to deform a template to fit the geometry of the target object. Our key contribution is a novel reinforcement learning framework that enables the network to also learn how to adjust, using pruning operations, the topology of the template to best fit the topology of the target object. We train the network in a supervised manner using a loss function that enforces smoothness and penalizes long edges in order to ensure high visual plausibility of the reconstructed 3D meshes. We evaluate the proposed approach on standard benchmarks such as ShapeNet, and in‐the‐wild using unseen real‐world images. We show that the proposed approach outperforms the state‐of‐the‐art in terms of the visual quality of the reconstructed 3D meshes, and also generalizes well to out‐of‐category images.Keywords
This publication has 40 references indexed in Scilit:
- Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis2017
- OctNet: Learning Deep 3D Representations at High Resolutions2017
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image2017
- 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction2016
- Multi-view 3D Models from Single Images with a Convolutional Network2016
- Deep Metric Learning via Lifted Structured Feature Embedding2016
- Structure-from-Motion Revisited2016
- Learning Category-Specific Deformable 3D Models for Object ReconstructionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Shape distributionsACM Transactions on Graphics, 2002
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence AlgorithmsInternational Journal of Computer Vision, 2002