Deep CNN-based methods have so far achieved the state of the art results in multi-view 3D object reconstruction. Despite the considerable progress, the two core modules of these methods - multi-view feature extraction and fusion, are usually investigated separately, and the object relations in different views are rarely explored. In this paper, inspired by the recent great success in self-attention-based Transformer models, we reformulate the multi-view 3D reconstruction as a sequence-to-sequence prediction problem and propose a new framework named 3D Volume Transformer (VolT) for such a task. Unlike previous CNN-based methods using a separate design, we unify the feature extraction and view fusion in a single Transformer network. A natural advantage of our design lies in the exploration of view-to-view relationships using self-attention among multiple unordered inputs. On ShapeNet - a large-scale 3D reconstruction benchmark dataset, our method achieves a new state-of-the-art accuracy in multi-view reconstruction with fewer parameters (70% less) than other CNN-based methods. Experimental results also suggest the strong scaling capability of our method. Our code will be made publicly available.
@article{arxiv.2103.12957,
title = {Multi-view 3D Reconstruction with Transformer},
author = {Dan Wang and Xinrui Cui and Xun Chen and Zhengxia Zou and Tianyang Shi and Septimiu Salcudean and Z. Jane Wang and Rabab Ward},
journal= {arXiv preprint arXiv:2103.12957},
year = {2021}
}