ChatHuman: Chatting about 3D Humans with Tools
Jing Lin, Yao Feng, Weiyang Liu, Michael J. Black
Abstract
Tool-Conditioned Transform Tool Docs The man in the dark blue shirt is preparing to sit down. Please find him out and estimate his 3d human pose. ⋆ Equal contribution. This work was done while YF and JL were at Meshcapade. specialized 3D outputs into comprehensible formats. Experiments demonstrate that ChatHuman surpasses existing models in both tool selection accuracy and overall performance across various 3D human tasks, and it supports interactive chatting with users. ChatHuman represents a significant step toward consolidating diverse analytical methods into a unified, robust system for 3D human tasks. Code and data are available at chathuman.github.io. What are the height, chest, hip, waist circumferences (in meter), and weight (in kg) of the person in the image? Height: 1.69 m Chest: 0.91 m Hip: 1.0 m Waist: 0.75 m Weight: 59.9 kg The woman is about 1.68 m tall, with a chest circumference of 0.90 m, a hip circumference of 0.93 m, a waist circumference of 0.78 m, weighs approximately 69 kg Height: 1.44 m Chest: 0.83 m Hip: 0.91 m Waist: 0.7 m Weight: 45.5 kg Tool ChatHuman GT Label What are the height, chest, hip, waist circumferences (in meter), and weight (in kg) of the person in the image?
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers3
- EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion TransformerYuxiao Yang, Hualian Sheng, Sijia Cai, Jing Lin et al.ICLR 2026 · 12 citations
- FrankenMotion: Part-level Human Motion Generation and CompositionChuqiao Li, Xianghui Xie, Yong Cao, Andreas Geiger et al.CVPR 2026 · 10 citations
- HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric ScenesKeliang Li, Hongze Shen, Hao Shi, Ruibing Hou et al.ICLR 2026 · 2 citations
Builds on31
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao et al.ICCV 2023 · 13,211 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 11,349 citations
Related papers
- ChatGarment: Garment Estimation, Generation and Editing via Large Language ModelsSiyuan Bian, Chenghao Xu, Yuliang Xiu, Artur Grigorev et al.CVPR 2025
- ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction GenerationLing-An Zeng, Guohong Huang, Yi-Lin Wei, Shengbo Gu et al.CVPR 2025
- CapHuman: Capture Your Moments in Parallel UniversesChao Liang, Fan Ma, Linchao Zhu, Yingying Deng et al.CVPR 2024
- Per Garment Capture and Synthesis for Real-time Virtual Try-onToby Long Hin Chong, I-Chao Shen, Nobuyuki Umetani, Takeo IgarashiUIST 2021 · 9 citations
- A Focused Human Body Model for Accurate Anthropometric Measurements ExtractionShuhang Chen, Xianliang Huang, Zhizhou Zhong, Juhong Guan et al.CVPR 2025
