InfiniHuman：具備精確控制的無限3D人體生成技術

InfiniHuman: Infinite 3D Human Creation with Precise Control

October 13, 2025

作者: Yuxuan Xue, Xianghui Xie, Margaret Kostyrko, Gerard Pons-Moll

cs.AI

摘要

生成逼真且可控的3D人體化身是一項長期存在的挑戰，尤其是在涵蓋廣泛屬性範圍時，如種族、年齡、服裝風格和細緻的體型。捕捉並註釋大規模的人類數據集以訓練生成模型成本高昂，且在規模和多樣性上受限。本文探討的核心問題是：能否通過蒸餾現有的基礎模型來生成理論上無界限、豐富註釋的3D人體數據？我們引入了InfiniHuman，這是一個協同蒸餾這些模型的框架，以最低成本生成豐富註釋的人體數據，並具備理論上的無限擴展性。我們提出了InfiniHumanData，這是一個完全自動化的流程，利用視覺-語言和圖像生成模型創建大規模多模態數據集。用戶研究表明，我們自動生成的身份與掃描渲染圖像無法區分。InfiniHumanData包含111,000個身份，涵蓋前所未有的多樣性。每個身份都配有多粒度文本描述、多視角RGB圖像、詳細服裝圖像和SMPL體型參數。基於此數據集，我們提出了InfiniHumanGen，這是一個基於擴散的生成流程，條件依賴於文本、體型和服裝資產。InfiniHumanGen能夠快速、逼真且精確可控地生成化身。大量實驗表明，在視覺質量、生成速度和可控性方面，我們的方法相較於最先進的技術有顯著提升。我們的方法通過實用且經濟的解決方案，實現了高質量化身的生成，並具備細粒度控制，達到理論上無界限的規模。我們將在https://yuxuan-xue.com/infini-human上公開自動數據生成流程、全面的InfiniHumanData數據集以及InfiniHumanGen模型。

English

Generating realistic and controllable 3D human avatars is a long-standing challenge, particularly when covering broad attribute ranges such as ethnicity, age, clothing styles, and detailed body shapes. Capturing and annotating large-scale human datasets for training generative models is prohibitively expensive and limited in scale and diversity. The central question we address in this paper is: Can existing foundation models be distilled to generate theoretically unbounded, richly annotated 3D human data? We introduce InfiniHuman, a framework that synergistically distills these models to produce richly annotated human data at minimal cost and with theoretically unlimited scalability. We propose InfiniHumanData, a fully automatic pipeline that leverages vision-language and image generation models to create a large-scale multi-modal dataset. User study shows our automatically generated identities are undistinguishable from scan renderings. InfiniHumanData contains 111K identities spanning unprecedented diversity. Each identity is annotated with multi-granularity text descriptions, multi-view RGB images, detailed clothing images, and SMPL body-shape parameters. Building on this dataset, we propose InfiniHumanGen, a diffusion-based generative pipeline conditioned on text, body shape, and clothing assets. InfiniHumanGen enables fast, realistic, and precisely controllable avatar generation. Extensive experiments demonstrate significant improvements over state-of-the-art methods in visual quality, generation speed, and controllability. Our approach enables high-quality avatar generation with fine-grained control at effectively unbounded scale through a practical and affordable solution. We will publicly release the automatic data generation pipeline, the comprehensive InfiniHumanData dataset, and the InfiniHumanGen models at https://yuxuan-xue.com/infini-human.