Creative Birds: Self-Supervised Single-View 3D Style Transfer

TL;DR

This paper introduces a novel self-supervised method for single-view 3D style transfer focusing on birds, combining shape and texture transfer using a dual residual gated network and semantic UV segmentation, achieving state-of-the-art results.

Contribution

The paper presents a new approach for 3D style transfer from single images, specifically for birds, with a novel shape transfer generator and semantic texture transfer module.

Findings

Achieves state-of-the-art performance on CUB dataset

Effective shape and texture transfer from two images

Semantic UV segmentation ensures consistent texture transfer

Abstract

In this paper, we propose a novel method for single-view 3D style transfer that generates a unique 3D object with both shape and texture transfer. Our focus lies primarily on birds, a popular subject in 3D reconstruction, for which no existing single-view 3D transfer methods have been developed.The method we propose seeks to generate a 3D mesh shape and texture of a bird from two single-view images. To achieve this, we introduce a novel shape transfer generator that comprises a dual residual gated network (DRGNet), and a multi-layer perceptron (MLP). DRGNet extracts the features of source and target images using a shared coordinate gate unit, while the MLP generates spatial coordinates for building a 3D mesh. We also introduce a semantic UV texture transfer module that implements textural style transfer using semantic UV segmentation, which ensures consistency in the semantic meaning of the transferred regions. This module can be widely adapted to many existing approaches. Finally, our method constructs a novel 3D bird using a differentiable renderer. Experimental results on the CUB dataset verify that our method achieves state-of-the-art performance on the single-view 3D style transfer task. Code is available in https://github.com/wrk226/creative_birds.