Recently, vision transformers have performed well in various computer vision tasks, including voxel 3D reconstruction. However, the windows of the vision transformer are not multi-scale, and there is no connection between the windows, which limits the accuracy of voxel 3D reconstruction. Therefore, we propose a voxel 3D reconstruction network based on shifted window attention. To the best of our knowledge, this is the first work to apply shifted window attention to voxel 3D reconstruction. Experimental results on ShapeNet verify our method achieves SOTA accuracy in single-view reconstruction.
@article{arxiv.2312.02725,
title = {R3D-SWIN:Use Shifted Window Attention for Single-View 3D Reconstruction},
author = {Chenhuan Li and Meihua Xiao and zehuan li and Fangping Chen and Shanshan Qiao and Dingli Wang and Mengxi Gao and Siyi Zhang},
journal= {arXiv preprint arXiv:2312.02725},
year = {2024}
}