SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion
Hsuan-I Ho, Jie Song, Otmar Hilliges
2024Year
40Top-tier citations
Abstract
Figure 1. Single-view textured human reconstruction. SiTH is a novel pipeline for creating high-quality and fully textured 3D human meshes from single images. We first hallucinate back-view appearances through an image-conditioned diffusion model, followed by the reconstruction of full-body textured meshes using both the front and back-view images. Our pipeline enables the creation of lifelike and diverse 3D humans from unseen photos (left) and AI-generated images (right).
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 papers40
- Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion ModelsYuxuan Xue, Xianghui Xie, Riccardo Marin, Gerard Pons-MollNeurIPS 2024 · 49 citations
- CARI4D: Category Agnostic 4D Reconstruction of Human-Object InteractionXianghui Xie, Bowen Wen, Yan Chang, Hesam Rabeti et al.CVPR 2026 · 16 citations
- Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs PriorYiqian Wu, Hao Xu, Xiangjun Tang, Xien Chen et al.SIGGRAPH 2024 · 14 citations
- SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human ReconstructionWenyue Chen, Peng Li, Wangguandong Zheng, Chengfeng Zhao et al.NeurIPS 2025 · 8 citations
- UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward PassMengfei Li, Peng Li, Zheng Zhang, Jiahao Lu et al.CVPR 2026 · 7 citations
Builds on46
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 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
Related papers
- SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human ReconstructionZechuan Zhang, Zongxin Yang, Yi YangCVPR 2024 · 44 citations
- ReFu: Refine and Fuse the Unobserved View for Detail-Preserving Single-Image 3D Human ReconstructionGyumin Shim, Minsoo Lee, Jaegul ChooACM MM 2022 · 4 citations
- 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
- ConTex-Human: Free-View Rendering of Human from a Single Image with Texture-Consistent SynthesisXiangjun Gao, Xiaoyu Li, Chaopeng Zhang, Qi Zhang et al.CVPR 2024
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit RemeshingPeng Li, Wangguandong Zheng, Yuan Liu, Tao Yu et al.CVPR 2025
