PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing
Peng Li, Wangguandong Zheng, Yuan Liu, Tao Yu, Yangguang Li, Xingqun Qi, Xiaowei Chi, Siyu Xia, Yan-Pei Cao, Wei Xue, Wenhan Luo, Yike Guo
2025Year
22Top-tier citations
Abstract
4 VAST https://penghtyx.github.io/PSHuman Figure 1. We introduce PSHuman, a diffusion-based full-body human reconstruction model. Given a single image of a clothed person, our method facilitates detailed geometry and realistic 3D human appearance across various poses within one minute.
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.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 881e3aff-8296-46a7-ba0d-e536dbae27f9Cited by top-tier papers22
- LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in SecondsLingteng Qiu, Xiaodong Gu, Peihao Li, Qi Zuo et al.ICCV 2025 · 19 citations
- Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable PhysicsXuan Li, Chang Yu, Wenxin Du, Ying Jiang et al.SIGGRAPH 2025 · 12 citations
- UP2You: Fast Reconstruction of Yourself from Unconstrained Photo CollectionsZeyu Cai, Ziyang Li, Xiaoben Li, Boqian Li et al.ICLR 2026 · 11 citations
- Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference OptimizationJingfeng Guo, Jian Liu, Jinnan Chen, Shiwei Mao et al.NeurIPS 2025 · 8 citations
- CMD: Controllable Multiview Diffusion for 3D Editing and Progressive GenerationPeng Li, Suizhi Ma, Jialiang Chen, Yuan Liu et al.SIGGRAPH 2025 · 8 citations
Builds on33
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationJunnan Li, Dongxu Li, Caiming Xiong, Steven C. H. HoiICML 2022 · 6,549 citations
- PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationShunsuke Saito, Zeng Huang, Ryota Natsume, Shigeo Morishima et al.ICCV 2019 · 1,411 citations
- Implicit Geometric Regularization for Learning ShapesAmos Gropp, Lior Yariv, Niv Haim, Matan Atzmon et al.ICML 2020 · 1,001 citations
- SyncDreamer: Generating Multiview-consistent Images from a Single-view ImageYuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long et al.ICLR 2024 · 685 citations
Related papers
- DiffHuman: Probabilistic Photorealistic 3D Reconstruction of HumansAkash Sengupta, Thiemo Alldieck, Nikos Kolotouros, Enric Corona et al.CVPR 2024 · 10 citations
- Diffusion-FOF: Single-View Clothed Human Reconstruction via Diffusion-Based Fourier Occupancy FieldYuanzhen Li, Fei Luo, Chunxia XiaoCVPR 2024
- DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single ImageHyeongjin Nam, Donghwan Kim, Jeongtaek Oh, Kyoung Mu LeeCVPR 2025
- GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human DataWentao Wang, Hang Ye, Fangzhou Hong, Xue Yang et al.NeurIPS 2025 · 6 citations
- Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar CreationXiyi Chen, Marko Mihajlovic, Shaofei Wang, Sergey Prokudin et al.CVPR 2024
