mlsanityData to 7 Oct 2026

R3D-SWIN:Use Shifted Window Attention for Single-View 3D Reconstruction

arXiv 2312.02725 ↗First posted 5 Dec 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 17 references that are in the map. First posted on arXiv 5 Dec 2023.

Builds on

16 of 17 references.

References · 16

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  6. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  7. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  8. 2017Learning a Multi-View Stereo Machinecited by 194
  9. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  10. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  11. 2021Multi-view 3D Reconstruction with Transformercited by 52
  12. 2021LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstructioncited by 25
4 more
  1. 20213D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformerscited by 15
  2. 2022GARNet: Global-Aware Multi-View 3D Reconstruction Network and the Cost-Performance Tradeoffcited by 8
  3. 2023UMIFormer: Mining the Correlations between Similar Tokens for Multi-View 3D Reconstructioncited by 7
  4. 2023Long-Range Grouping Transformer for Multi-View 3D Reconstructioncited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Bridging Text and Video Generation: A Surveycited by 2