Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details

TL;DR

Hunyuan3D 2.5 introduces advanced 3D diffusion models with a new shape foundation and improved texture generation, achieving high-fidelity, detailed 3D assets with sharp shapes and realistic textures.

Contribution

The paper presents Hunyuan3D 2.5, featuring a new shape foundation model LATTICE and enhanced texture generation with PBR, significantly improving 3D asset quality over previous methods.

Findings

Outperforms previous methods in shape quality and detail

Generates sharp, smooth, and realistic 3D shapes

Achieves superior end-to-end texture quality

Abstract

In this report, we present Hunyuan3D 2.5, a robust suite of 3D diffusion models aimed at generating high-fidelity and detailed textured 3D assets. Hunyuan3D 2.5 follows two-stages pipeline of its previous version Hunyuan3D 2.0, while demonstrating substantial advancements in both shape and texture generation. In terms of shape generation, we introduce a new shape foundation model -- LATTICE, which is trained with scaled high-quality datasets, model-size, and compute. Our largest model reaches 10B parameters and generates sharp and detailed 3D shape with precise image-3D following while keeping mesh surface clean and smooth, significantly closing the gap between generated and handcrafted 3D shapes. In terms of texture generation, it is upgraded with phyiscal-based rendering (PBR) via a novel multi-view architecture extended from Hunyuan3D 2.0 Paint model. Our extensive evaluation shows that Hunyuan3D 2.5 significantly outperforms previous methods in both shape and end-to-end texture generation.