Fine Detailed Texture Learning for 3D Meshes with Generative Models

TL;DR

This paper introduces a progressive method for reconstructing high-quality textured 3D meshes from images, utilizing innovative attention and embedding techniques to enhance texture alignment and quality.

Contribution

It proposes a novel two-stage framework with attention and embedding enhancements for improved 3D texture learning from images.

Findings

Significant improvements on Tripod, Pascal 3D+, and CUB datasets.

Outperforms previous methods in textured 3D model quality.

Effective multi-view and single-view reconstruction results.

Abstract

This paper presents a method to reconstruct high-quality textured 3D models from both multi-view and single-view images. The reconstruction is posed as an adaptation problem and is done progressively where in the first stage, we focus on learning accurate geometry, whereas in the second stage, we focus on learning the texture with a generative adversarial network. In the generative learning pipeline, we propose two improvements. First, since the learned textures should be spatially aligned, we propose an attention mechanism that relies on the learnable positions of pixels. Secondly, since discriminator receives aligned texture maps, we augment its input with a learnable embedding which improves the feedback to the generator. We achieve significant improvements on multi-view sequences from Tripod dataset as well as on single-view image datasets, Pascal 3D+ and CUB. We demonstrate that our method achieves superior 3D textured models compared to the previous works. Please visit our web-page for 3D visuals.