Publications
* indicates equal contribution
2026
- Yue Ma, Pengjie Song, Xinyu Wang, Yi He, Zeqian Long, Fangneng Zhan, Kaichen Zhou, Hongyu Liu, Hongfa Wang, Peihao Li, Haoyang Huang, Nan Duan, Qifeng Chen. Decoupling Action from Egocentric Observation for World Simulation. NeurIPS 2026
- Muyu Xu, Fangneng Zhan, Yu Wei, Ling Shao, Shijian Lu. BudSplat: Feed-forward 3D Gaussian Splatting under a Rendering Budget. NeurIPS 2026
- Yifeng Liu, Yuzhen Chen, Bingyang Wang, Chengqi Li, Jingyi Lu, Han Li, Yuelei Li, Mazeyu Ji, Kaichen Zhou, Mengyu Wang, Fangneng Zhan. Act2See: Structured Articulated Representations through Robot Interaction. RSS 2026 FM4RoboPlan Workshop | Paper | Project | Code
- Kaichen Zhou*, Zeyang Bai*, Xinhai Chang*, Mengyu Wang, Paul Liang†, Fangneng Zhan†. Stream3D: Sequential Multi-View 3D Generation via Evidential Memory. ECCV 2026 OpenSUN3D Workshop | Paper | Project | Code (Award Candidate)
- Kaichen Zhou, Xinhai Chang, Taewhan Kim, Jiadong Zhang, Yang Cao, Chufei Peng, Fangneng Zhan, Hao Zhao, Hao Dong, Kai Ming Ting, Ye Zhu. RAD: A dataset and benchmark for real-life anomaly detection with robotic observations. Preprint 2026 | Paper | Code
- Keming Wu, Zuhao Yang, Kaichen Zhang, Shizun Wang, Haowei Zhu, Sicong Leng, Zhongyu Yang, Qijie Wang, Sudong Wang, Ziting Wang, Zili Wang, Hui Zhang, Haonan Wang, Hang Zhou, Yifan Pu, Xingxuan Li, Fangneng Zhan, Bo Li, Lidong Bing, Yuxin Song, Ziwei Liu, Wenhu Chen, Jingdong Wang, Xinchao Wang, Xiaojuan Qi, Shijian Lu, Bin Wang. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling. Preprint 2026 | Paper | Project | Code
- Freeman Cheng, Botao Ye, Xueting Li, Junqi You, Fangneng Zhan, Ming-Hsuan Yang. ReCoSplat: Autoregressive Feed-Forward Gaussian Splatting Using Render-and-Compare. Preprint 2026 | Paper | Project | Code
- Kaichen Zhou*, Yuzhen Chen*, Fangneng Zhan, Hang Hua, Grace Chen, Xinhai Chang, Ao Qu, Yilun Du, Zhuang Liu, Paul Pu Liang, Mengyu Wang. GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation. ECCV 2026 | Paper | Project (WMAS Workshop Best Paper Award Runner-up)
- Leslie Gu, Junhwa Hur, Charles Herrmann, Fangneng Zhan, Todd Zickler, Deqing Sun, Hanspeter Pfister. GeCo: A Differentiable Geometric Consistency Metric for Video Generation. ECCV 2026 | Paper | Code
- Muyu Xu, Fangneng Zhan, Yu Wei, Hanspeter Pfister, Shijian Lu. AVSplat:Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning. ECCV 2026 | Paper
- Xinyu Wang, Chongbo Zhao, Fangneng Zhan, Yue Ma. LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing. ECCV 2026 | Paper | Code
- Yue Ma, Xu Ye, Qinghe Wang†, Yucheng Wang, Hongyu Liu, Yinhan Zhang, Xinyu Wang, Yuanpeng Che, Shanhui Mo, Paul Liang, Fangneng Zhan†, Qifeng Chen. EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation. SIGGRAPH 2026 | Paper | Project | Code
- Hansen Lillemark*, Benhao Huang*, Fangneng Zhan, Yilun Du, T. Anderson Keller. Flow Equivariant World Modeling for Partially Observed Dynamic Environments. ICML 2026 | Paper | Project | Code
- Yifan Liu, Fangneng Zhan, Kaichen Zhou, Yilun Du, Paul Pu Liang, Hanspeter Pfister. Abstract 3D Perception for Spatial Intelligence in Vision-Language Models. CVPR 2026 | Paper | Project
- Yifan Liu, Fangneng Zhan, Haowen Sun, Katerina Fragkiadaki, Hanspeter Pfister. RoboTAG: End-to-end Robot Pose Estimation via Topological Alignment Graph. CVPR 2026 | Paper
- Tianling Xu, Shengzhe Gan, Leslie Gu, Yuelei Li, Fangneng Zhan, Hanspeter Pfister. AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance. CVPR 2026 | Paper | Project | Code
- Kaichen Zhou, Yuhan Wang, Grace Chen, Xinhai Chang, Gaspard Beaudouin, Fangneng Zhan, Paul Pu Liang, Mengyu Wang. PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception. ICLR 2026 | Paper | Project | Code
- Muyu Xu, Fangneng Zhan, Xiaoqin Zhang, Ling Shao, Shijian Lu. MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation. AAAI 2026 | Paper
- Jiahui Zhang*, Yuelei Li*, Anpei Chen, Muyu Xu, Kunhao Liu, Jianyuan Wang, Xiaoxiao Long, Hanxue Liang, Zexiang Xu, Hao Su, Christian Theobalt, Christian Rupprecht, Andrea Vedaldi, Kaichen Zhou, Hanspeter Pfister, Paul Pu Liang, Shijian Lu, Fangneng Zhan. Advances in Feed-Forward 3D Reconstruction and View Synthesis. CGF 2026 | Paper | Project
2025
- Pramod Rao, Xilong Zhou, Abhimitra Meka, Gereon Fox, Mallikarjun B R, Fangneng Zhan, Tim Weyrich, Bernd Bickel, Hanspeter Pfister, Wojciech Matusik, Thabo Beeler, Mohamed Elgharib, Marc Habermann, Christian Theobalt. 3DPR: Single Image 3D Portrait Relighting with Generative Priors. SIGGRAPH Asia 2025 | Paper | Project | Code
- Jiahui Zhang, Fangneng Zhan, Ling Shao, Shijian Lu. SOGS: Second-Order Anchor for Advanced 3D Gaussian Splatting. CVPR 2025 | Paper
- Qian Wang, Abdelrahman Eldesokey, Mohit Mendiratta, Fangneng Zhan, Adam Kortylewski, Christian Theobalt, Peter Wonka. Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models. CVPR 2025 | Paper | Project | Code
- Yuelei Li, Hyunjin Kim, Fangneng Zhan, Ri-Zhao Qiu, Mazeyu Ji, Xiaojun Shan, Paul Pu Liang, Hanspeter Pfister, Xiaolong Wang. Visual Acoustic Fields. Preprint 2025 | Paper | Project
2024
- Fangneng Zhan*, Hanxue Liang*, Michael Niemeyer, Yifan Wang, Michael Oechsle, Adam Kortylewski, Cengiz Oztireli, Gordon Wetzstein, Christian Theobalt. Evolutive Rendering Models. Preprint 2024 | Paper | Project
- Yu Chi, Fangneng Zhan, Sibo Wu, Christian Theobalt, Adam Kortylewski. DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields. ECCV 2024 | Paper
- Pramod Ramesh Rao, Mallikarjun B R, Abhimitra Meka, Gereon Fox, Fangneng Zhan, Tim Weyrich, Bernd Bickel, Hanspeter Pfister, Wojciech Matusik, Mohamed Elgharib, Christian Theobalt. Lite2Relight: 3D-aware Single Image Portrait Relighting. SIGGRAPH 2024 | Paper | Project | Code
- Heming Zhu, Fangneng Zhan, Christian Theobalt, Marc Habermann. TriHuman: A Real-time and Controllable Tri-plane Representation for Detailed Human Geometry and Appearance Synthesis. TOG 2024 | Paper | Project | Code
- Kunhao Liu, Fangneng Zhan, Muyu Xu, Christian Theobalt, Ling Shao, Shijian Lu. StyleGaussian: Instant 3D Style Transfer with Gaussian Splatting. SIGGRAPH Asia 2024 (Technical Communications) | Paper | Project | Code
- Jiahui Zhang, Fangneng Zhan, Muyu Xu, Shijian Lu, Eric P. Xing. FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization. CVPR 2024 | Paper | Project
- Zuhao Yang, Fangneng Zhan, Kunhao Liu, Jiahui Zhang, Muyu Xu, Christian Theobalt, Eric Xing, Shijian Lu. AI-Generated Images as Data Source: The Dawn of Synthetic Era. Preprint 2024 | Paper
2023
- Kunhao Liu, Fangneng Zhan, Jiahui Zhang, Muyu Xu, Yingchen Yu, Abdulmotaleb El Saddik, Christian Theobalt, Eric Xing, Shijian Lu. 3D Open-vocabulary Segmentation with Foundation Models. NeurIPS 2023 | Paper | Code
- Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang, Shijian Lu, Lingjie Liu, Adam Kortylewski, Christian Theobalt, Eric Xing. Multimodal Visual Synthesis and Editing: The Generative AI Era. TPAMI 2023 | Paper | Project | Code (Top 50 Most Popular TPAMI Paper)
- Muyu Xu, Fangneng Zhan, Jiahui Zhang, Rongliang Wu, Yingchen Yu, Christian Theobalt, Shijian Lu. WaveNeRF: Wavelet-based Generalizable Neural Radiance Fields. ICCV 2023 | Paper
- Jiahui Zhang, Fangneng Zhan, Rongliang Wu, Yingchen Yu, Kunhao Liu, Christian Theobalt, Shijian Lu. Pose-Free Neural Radiance Fields via Implicit Pose Regularization. ICCV 2023 | Paper
- Pramod Rao, Mallikarjun B R, Gereon Fox, Tim Weyrich, Bernd Bickel, Hanspeter Pfister, Wojciech Matusik, Fangneng Zhan, Ayush Tewari, Christian Theobalt, Mohamed Elgharib. A Deeper Analysis of Volumetric Relightable Fields. IJCV 2023 | Paper | Project (Invited Paper, BMVC Best Paper Award Honourable Mention)
- Fangneng Zhan, Lingjie Liu, Adam Kortylewski, Christian Theobalt. General Neural Gauge Fields. ICLR 2023 | Paper | Project | Code
- Rongliang Wu, Yingchen Yu, Fangneng Zhan, Jiahui Zhang, Shijian Lu. POCE: Pose-Controllable Expression Editing with Unpaired Training Images. TIP 2023 | Paper
- Kunhao Liu, Fangneng Zhan, Yiwen Chen, Jiahui Zhang, Yingchen Yu, Shijian Lu. StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields. CVPR 2023 | Paper | Project | Code
- Kaiwen Cui, Yingchen Yu, Fangneng Zhan, Shengcai Liao, Shijian Lu, Eric Xing. KD-GAN: Data Limited Image Generation via Knowledge Distillation. CVPR 2023 | Paper
- Jiahui Zhang, Fangneng Zhan, Christian Theobalt, Shijian Lu. Regularized Vector Quantization for Tokenized Image Synthesis. CVPR 2023 | Paper
- Kaiwen Cui, Rongliang Wu, Fangneng Zhan, Shijian Lu. Face Transformer: Towards High Fidelity and Accurate Face Swapping. CVPRW 2023 | Paper
- Rongliang Wu, Yingchen Yu, Fangneng Zhan, Jiahui Zhang, Shijian Lu, Eric Xing. Audio-Driven Talking Face Generation with Diverse yet Realistic Facial Animations. PR 2023 | Paper
2022
- Jiaxing Huang, Kaiwen Cui, Dayan Guan, Aoran Xiao, Fangneng Zhan, Shijian Lu, Shengcai Liao, Eric Xing. Masked Generative Adversarial Networks are Robust Generation Learners. NeurIPS 2022 | Paper (Spotlight)
- Yingchen Yu*, Fangneng Zhan*, Rongliang Wu, Jiahui Zhang, Kaiwen Cui, Aoran Xiao, Shijian Lu, Chunyan Miao. Bi-level Feature Alignment for Versatile Image Translation and Manipulation. ECCV 2022 | Paper | Code
- Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang, Kaiwen Cui, Changgong Zhang, Shijian Lu. Auto-regressive Image Modeling with Integrated Quantization. ECCV 2022 | Paper | Code (Oral Presentation)
- Jiahui Zhang, Fangneng Zhan, Rongliang Wu, Yingchen Yu, Wenqing Zhang, Song Bai, Xiaoqin Zhang, Shijian Lu. VMRF: View Matching Neural Radiance Fields. ACM MM 2022 | Paper
- Yingchen Yu, Fangneng Zhan, Rongliang Wu, Jiahui Zhang, Shijian Lu, Miaomiao Cui, Xuansong Xie, Xian-Sheng Hua, Chunyan Miao. Towards Counterfactual Image Manipulation via CLIP. ACM MM 2022 | Paper | Code
- Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang, Shijian Lu, Changgong Zhang. Marginal Correspondence for Conditional Image Generation. CVPR 2022 | Paper | Code (Oral Presentation)
- Chuhui Xue, Zichen Tian, Fangneng Zhan, Shijian Lu, Song Bai. Fourier Document Restoration for Robust Document Dewarping and Recognition. CVPR 2022 | Paper
- Fangneng Zhan, Yingchen Yu, Kaiwen Cui, Gongjie Zhang, Shijian Lu, Jianxiong Pan, Changgong Zhang, Feiying Ma, Xuansong Xie, Chunyan Miao. Modulated Contrast for Versatile Image Synthesis. CVPR 2022 | Paper | Code
- Changgong Zhang, Fangneng Zhan, Yingchen Yu, Rongliang Wu, Wenbo Hu, Shijian Lu, Feiying Ma, Xuansong Xie, Ling Shao. GMLight: Lighting Estimation via Geometric Distribution Approximation. TIP 2022 | Paper | Code
- Kaiwen Cui, Jiaxing Huang, Zhipeng Luo, Gongjie Zhang, Fangneng Zhan, Shijian Lu. GenCo: Generative Cotraining on Data Limited Image Generation. AAAI 2022 | Paper | Code
- Aoran Xiao, Jiaxing Huang, Dayan Guan, Fangneng Zhan, Shijian Lu. Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation. AAAI 2022 | Paper | Code
2021
- Fangneng Zhan, Yingchen Yu, Kaiwen Cui, Gongjie Zhang, Shijian Lu, Jianxiong Pan, Changgong Zhang, Feiying Ma, Xuansong Xie, Chunyan Miao. Unbalanced Feature Transport for Exemplar-based Image Translation. CVPR 2021 | Paper | Project | Code
- Yingchen Yu, Fangneng Zhan, Shijian Lu, Jianxiong Pan, Feiying Ma, Xuansong Xie, Chunyan Miao. WaveFill: A Wavelet-based Generation Network for Image Inpainting. ICCV 2021 | Paper | Code (Oral Presentation)
- Fangneng Zhan*, Changgong Zhang*, Wenbo Hu, Shijian Lu, Feiying Ma, Xuansong Xie, Ling Shao. Sparse Needlets for Lighting Estimation with Spherical Transport Loss. ICCV 2021 | Paper | Code
- Fangneng Zhan*, Changgong Zhang*, Yingchen Yu, Yuan Chang, Shijian Lu, Feiying Ma, Xuansong Xie. EMLight: Lighting Estimation via Spherical Distribution Approximation. AAAI 2021 | Paper | Code
- Yingchen Yu*, Fangneng Zhan*, Rongliang Wu, Jianxiong Pan, Kaiwen Cui, Shijian Lu, Feiying Ma, Xuansong Xie, Chunyan Miao. Diverse Image Inpainting with Bidirectional and Autoregressive Transformers. ACM MM 2021 | Paper (Oral Presentation)
- Wenbo Hu, Changgong Zhang, Fangneng Zhan, Lei Zhang, Tien-Tsin Wong. Conditional Directed Graph Convolution for 3D Human Pose Estimation. ACM MM 2021 | Paper | Project
2020
- Changgong Zhang, Fangneng Zhan, Shijian Lu, Feiying Ma, Xuansong Xie. Adversarial Image Composition with Auxiliary Illumination. ACCV 2020 | Paper (Oral Presentation)
2019
- Fangneng Zhan, Chuhui Xue, Shijian Lu. GA-DAN: Geometry-Aware Domain Adaptation with Generative Adversarial Networks. ICCV 2019 | Paper
- Changgong Zhang, Fangneng Zhan. Spatial-Aware GAN for Unsupervised Person Re-identification. ICPR 2019 | Paper
- Fangneng Zhan, Hongyuan Zhu, Shijian Lu. Spatial Fusion GAN for Image Synthesis. CVPR 2019 | Paper
- Fangneng Zhan, Shijian Lu. ESIR: End-to-end Scene Recognition via Iterative Image Transformation. CVPR 2019 | Paper