Long-Range Grouping Transformer for Multi-View 3D Reconstruction

TL;DR

This paper introduces LRGT, a transformer-based network with long-range grouping attention for multi-view 3D reconstruction, effectively handling complex view information and achieving state-of-the-art accuracy on ShapeNet.

Contribution

The paper proposes a novel long-range grouping attention mechanism and a progressive upsampling decoder, improving multi-view 3D reconstruction performance.

Findings

Achieves state-of-the-art accuracy on ShapeNet dataset.

Effectively handles complex multi-view information with LGA.

Outperforms previous methods in 3D reconstruction quality.

Abstract

Nowadays, transformer networks have demonstrated superior performance in many computer vision tasks. In a multi-view 3D reconstruction algorithm following this paradigm, self-attention processing has to deal with intricate image tokens including massive information when facing heavy amounts of view input. The curse of information content leads to the extreme difficulty of model learning. To alleviate this problem, recent methods compress the token number representing each view or discard the attention operations between the tokens from different views. Obviously, they give a negative impact on performance. Therefore, we propose long-range grouping attention (LGA) based on the divide-and-conquer principle. Tokens from all views are grouped for separate attention operations. The tokens in each group are sampled from all views and can provide macro representation for the resided view. The richness of feature learning is guaranteed by the diversity among different groups. An effective and efficient encoder can be established which connects inter-view features using LGA and extract intra-view features using the standard self-attention layer. Moreover, a novel progressive upsampling decoder is also designed for voxel generation with relatively high resolution. Hinging on the above, we construct a powerful transformer-based network, called LRGT. Experimental results on ShapeNet verify our method achieves SOTA accuracy in multi-view reconstruction. Code will be available at https://github.com/LiyingCV/Long-Range-Grouping-Transformer.