StdGEN: Semantic-Decomposed 3D Character Generation from Single Images

TL;DR

StdGEN is a fast, high-quality pipeline that generates detailed, semantically decomposed 3D characters from single images, advancing virtual reality, gaming, and filmmaking applications.

Contribution

It introduces a novel transformer-based model and semantic surface extraction scheme for efficient, detailed 3D character reconstruction from minimal input.

Findings

Achieves state-of-the-art results in 3D anime character generation

Generates detailed, decomposable 3D characters in three minutes

Surpasses existing methods in geometry, texture, and semantic separation

Abstract

We present StdGEN, an innovative pipeline for generating semantically decomposed high-quality 3D characters from single images, enabling broad applications in virtual reality, gaming, and filmmaking, etc. Unlike previous methods which struggle with limited decomposability, unsatisfactory quality, and long optimization times, StdGEN features decomposability, effectiveness and efficiency; i.e., it generates intricately detailed 3D characters with separated semantic components such as the body, clothes, and hair, in three minutes. At the core of StdGEN is our proposed Semantic-aware Large Reconstruction Model (S-LRM), a transformer-based generalizable model that jointly reconstructs geometry, color and semantics from multi-view images in a feed-forward manner. A differentiable multi-layer semantic surface extraction scheme is introduced to acquire meshes from hybrid implicit fields reconstructed by our S-LRM. Additionally, a specialized efficient multi-view diffusion model and an iterative multi-layer surface refinement module are integrated into the pipeline to facilitate high-quality, decomposable 3D character generation. Extensive experiments demonstrate our state-of-the-art performance in 3D anime character generation, surpassing existing baselines by a significant margin in geometry, texture and decomposability. StdGEN offers ready-to-use semantic-decomposed 3D characters and enables flexible customization for a wide range of applications. Project page: https://stdgen.github.io