Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images

TL;DR

Pix2Vox++ introduces a multi-scale, context-aware framework for 3D object reconstruction from single or multiple images, overcoming RNN limitations and achieving superior accuracy and efficiency.

Contribution

The paper proposes a novel encoder-decoder architecture with a multi-scale fusion module and refiner, improving 3D reconstruction consistency and quality over existing RNN-based methods.

Findings

Outperforms state-of-the-art methods on ShapeNet, Pix3D, and Things3D datasets.

Achieves higher accuracy and efficiency in 3D reconstruction.

Effectively handles single-view and multi-view inputs.

Abstract

Recovering the 3D shape of an object from single or multiple images with deep neural networks has been attracting increasing attention in the past few years. Mainstream works (e.g. 3D-R2N2) use recurrent neural networks (RNNs) to sequentially fuse feature maps of input images. However, RNN-based approaches are unable to produce consistent reconstruction results when given the same input images with different orders. Moreover, RNNs may forget important features from early input images due to long-term memory loss. To address these issues, we propose a novel framework for single-view and multi-view 3D object reconstruction, named Pix2Vox++. By using a well-designed encoder-decoder, it generates a coarse 3D volume from each input image. A multi-scale context-aware fusion module is then introduced to adaptively select high-quality reconstructions for different parts from all coarse 3D volumes to obtain a fused 3D volume. To further correct the wrongly recovered parts in the fused 3D volume, a refiner is adopted to generate the final output. Experimental results on the ShapeNet, Pix3D, and Things3D benchmarks show that Pix2Vox++ performs favorably against state-of-the-art methods in terms of both accuracy and efficiency.