TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification

Guan Luo, Xiu Li, Rui Chen, Xuanyu Yi, Jing Lin, Chia-Hao Chen, Jiahang Liu, Song-Hai Zhang, Jianfeng Zhang

Project

• we introduce TopoMesh, a sparse voxel-based VAE that unifies both GT and predicted meshes under a shared Dual Marching Cubes topological framework. This establishes explicit correspondences at the vertex and face level, allowing us to derive explicit mesh-level supervision signals for topology, vertex positions, and face orientations with clear gradients.

LaFiTe: A Generative Latent Field for 3D Native Texturing

Chia-Hao Chen, Zi-Xin Zou, Yan-Pei Cao, Ze Yuan, Guan Luo, Xiaojuan Qi, Ding Liang, Song-Hai Zhang, Yuan-Chen Guo

Project

• We introduce LaFiTe, a framework that addresses this challenge by learning to generate textures as a 3D generative sparse latent color field.

Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets

Seed3D Team

Project

• We present Seed3D 1.0, a foundation model that generates simulation-ready 3D assets from single images, addressing the scalability challenge while maintaining physics rigor. Unlike existing 3D generation models, our system produces assets with accurate geometry, well-aligned textures, and realistic physically-based materials.

MS3D: High-Quality 3D Generation via Multi-Scale Representation Modeling

Guan Luo, Jianfeng Zhang

Project

• we introduce MS3D, a novel multi-scale 3D reconstruction framework. At its core, we introduce a hierarchical structured latent representation for multi-scale modeling, coupled with a multi-scale feature extraction and integration mechanism, which enables progressive reconstruction, effectively decomposing the complex task of detailed geometry reconstruction into a sequence of easier steps.

3D Gaussian Editing With A Single Image

Guan Luo, Tian-Xing Xu, Ying-Tian Liu, Xiao-Xiong Fan, Fang-Lue Zhang, Song-Hai Zhang

Project

• we introduce a novel single-image-driven 3D scene editing approach based on 3D Gaussian Splatting, enabling intuitive manipulation via directly editing the content on a 2D image plane. Our method learns to optimize the 3D Gaussians to align with an edited version of the image rendered from a user-specified viewpoint of the original scene.

Threestudio: A unified framework for 3d content generation

Yuan-Chen Guo, Ying-Tian Liu, Ruizhi Shao, Christian Laforte, Vikram Voleti, Guan Luo, Chia-Hao Chen, Zi-Xin Zou, Chen Wang, Yan-Pei Cao, Song-Hai Zhang

Project

• We introduce threestudio, an open-source, unified, and modular framework specifically designed for 3D content generation. This framework extends diffusion-based 2D image generation models to 3D generation guidance while incorporating conditions such as text and images. We delineate the modular architecture and design of each component within threestudio.