Teaser
High-quality 3D shape samples from our largest TripoSG model. Covering various complex structures, diverse styles, imaginative designs, multi-object compositions, and richly detailed outputs, demonstrates its powerful generation capabilities.
Abstract
Recent advancements in diffusion techniques have propelled image and video generation to unprecedented levels of quality, significantly accelerating the deployment and application of generative AI. However, 3D shape generation technology has so far lagged behind, constrained by limitations in 3D data scale, complexity of 3D data processing, and insufficient exploration of advanced techniques in the 3D domain. Current approaches to 3D shape generation face substantial challenges in terms of output quality, generalization capability, and alignment with input conditions. We present TripoSG, a new streamlined shape diffusion paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images. Specifically, we propose: 1) A large-scale rectified flow transformer for 3D shape generation, achieving state-of-the-art fidelity through training on extensive, high-quality data. 2) A hybrid supervised training strategy combining SDF, normal, and eikonal losses for 3D VAE, achieving high-quality 3D reconstruction performance. 3) A data processing pipeline to generate 2 million high-quality 3D samples, highlighting the crucial rules for data quality and quantity in training 3D generative models. Through comprehensive experiments, we have validated the effectiveness of each component in our new framework. The seamless integration of these parts has enabled TripoSG to achieve state-of-the-art performance in 3D shape generation. The resulting 3D shapes exhibit enhanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input images. Moreover, TripoSG demonstrates improved versatility in generating 3D models from diverse image styles and contents, showcasing strong generalization capabilities. To foster progress and innovation in the field of 3D generation, we will make our model publicly available.
Rectified Flow Pipeline
Left: the overall architecture of TripoSG. Middle: the detailed internal module of each block. Right: the detailed internal components of the MoE.
VAE Pipeline
TripoSG’s transformer-based VAE architecture. The upper is the encoder and the lower is the decoder.
Data Processe Pipeline
Demonstration of the TripoSG data-building system. I: Data scoring procedure; II: Data filtering procedure; III: Data fixing and augmentation procedure. IV: Field data producing procedure.
Results Comparison
Comparison of 3D generation performance of TripoSG and other previous state-of-the-art methods under the same image input.
More Texture-free 3D Shapes Generation Results
A diverse array of texture-free 3D shapes generated by TripoSG. The first image in each case is the input image, and the remaining four are multi-views rendered from the generated model.
More Textured 3D Shapes Generation Results
A diverse array of textured 3D shapes generated by TripoSG. The first image in each case is the input image, and the remaining four are multi-views rendered from the generated model.
Citation
@article{li2025triposg,
title={TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models},
author={Li, Yangguang and Zou, Zi-Xin and Liu, Zexiang and Wang, Dehu and Liang, Yuan and Yu, Zhipeng and Liu, Xingchao and Guo, Yuan-Chen and Liang, Ding and Ouyang, Wanli and others},
journal={arXiv preprint arXiv:2502.06608},
year={2025}
}