Zian Wang

I am a senior research scientist and research manager at NVIDIA Spatial Intelligence Lab. I lead a research team working on generative world models and video foundation models that are high-quality, controllable, and efficient.

I defended my PhD at University of Toronto, advised by Sanja Fidler. My work on inverse rendering, scene representations, and generative rendering has received oral presentations and a best paper award. Before coming to Toronto, I did my bachelor at Tsinghua University.

Hiring: We have research scientist openings for candidates with strong experiences in large-scale video diffusion, VLMs, and multi-modality models.

We are proud to collaborate with world-class PhD students through research internships. Applications typically open in September.

Email / Google Scholar / LinkedIn / Twitter

Research

	PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion Yifan Lu, Qi Wu, Jay Zhangjie Wu, Zian Wang, Huan Ling, Sanja Fidler, Xuanchi Ren preprint, 2026 project page / pdf / code / model / bibtex 🚀 PiD is officially integrated into ComfyUI (MR, model). Many thanks to the community for the support!
	Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Fangfu Liu, Kai He, Tianchang Shen, Tianshi Cao, Sanja Fidler, Yueqi Duan, Jun Gao, Igor Gilitschenski^†, Zian Wang^†, Xuanchi Ren^† preprint, 2026 project page / pdf / code / bibtex 🔥 Hugging Face #1 Paper of the day
	NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation Aarti Basant, Amlan Kar, Despoina Paschalidou, Fangyin Wei, Francesco Ferroni, Guillermo Garcia Cobo, Haithem Turki, Huan Ling, Jaewoo Seo, Jialiang Wang, James Lucas, Jay Wu, Jonathan Lorraine, Jun Gao, Kai He, Katarina Tothova, Kevin Xie, Michal Tyszkiewicz, Qi Wu, Riccardo de Lutio, Ruilong Li, Sanja Fidler, Seung Wook Kim, Tianchang Shen, Tianshi Cao, Tobias Pfaff, William Lew, Xuanchi Ren, Yifan Lu, Zan Gojcic, Zian Wang NVIDIA Technical Report, 2026 project page / pdf / code / model / data samples
	DiffusionHarmonizer: Towards Temporal Reasoning for Image Editing and World Simulation Yuxuan Zhang, Katarina Tothova, Zian Wang, Kangxue Yin, Haithem Turki, Riccardo de Lutio, Yen-Yu Chang, Or Litany, Sanja Fidler, Zan Gojcic CVPR, 2026 project page / pdf / bibtex
	ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Tianshi Cao, Kai He, Yifan Lu, Ruiyuan Gao, Enze Xie, Shiyi Lan, Jose M. Alvarez, Jun Gao, Sanja Fidler, Zian Wang, Huan Ling* ICLR, 2026 project page / pdf / code / bibtex
	LuxDiT: Lighting Estimation with Video Diffusion Transformer Ruofan Liang, Kai He, Zan Gojcic, Igor Gilitschenski, Sanja Fidler, Nandita Vijaykumar^†, Zian Wang^† NeurIPS, 2025 project page / pdf / code / bibtex
	UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting Kai He, Ruofan Liang, Jacob Munkberg, Jon Hasselgren, Nandita Vijaykumar, Alexander Keller, Sanja Fidler, Igor Gilitschenski^†, Zan Gojcic^†, Zian Wang^† NeurIPS, 2025 (Spotlight Presentation) project page / pdf / code / demo video / twitter thread / bibtex
	Controllable Weather Synthesis and Removal with Video Diffusion Models Chih-Hao Lin, Zian Wang, Ruofan Liang, Yuxuan Zhang, Sanja Fidler, Shenlong Wang, Zan Gojcic ICCV, 2025 project page / pdf / demo video / twitter thread / bibtex
	VideoMat: Extracting PBR Materials from Video Diffusion Models Jacob Munkberg, Zian Wang, Ruofan Liang, Tianchang Shen, Jon Hasselgren EGSR, 2025 project page / pdf / video / bibtex
	DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models Ruofan Liang, Zan Gojcic, Huan Ling, Jacob Munkberg, Jon Hasselgren, Chih-Hao Lin, Jun Gao, Alexander Keller, Nandita Vijaykumar, Sanja Fidler, Zian Wang** CVPR, 2025 (Oral Presentation) project page / pdf / supp video / demo / code / twitter thread / bibtex 🚀 [Open Source Model] Cosmos-Transfer1-DiffusionRenderer is a major upgrade with significantly improved quality—powered by NVIDIA Cosmos and enhanced data curation. Try the Cosmos version: demo / code / model / blog
	Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering Ruofan Liang, Zan Gojcic, Merlin Nimier-David, David Acuna, Nandita Vijaykumar, Sanja Fidler, Zian Wang ECCV, 2024 project page / pdf / bibtex
	Adaptive Shells for Efficient Neural Radiance Field Rendering Zian Wang, Tianchang Shen, Merlin Nimier-David, Nicholas Sharp, Jun Gao, Alexander Keller, Sanja Fidler, Thomas Müller, Zan Gojcic ACM Transactions on Graphics (SIGGRAPH Asia), 2023* (Best Paper Award) project page / arxiv / pdf / supp / twitter thread / bibtex
	Neural LiDAR Fields for Novel View Synthesis Shengyu Huang, Zan Gojcic, Zian Wang, Francis Williams, Yoni Kasten, Sanja Fidler, Konrad Schindler, Or Litany ICCV, 2023 project page / pdf / bibtex / tech blog
	Flexible Isosurface Extraction for Gradient-Based Mesh Optimization Tianchang Shen, Jacob Munkberg, Jon Hasselgren, Kangxue Yin, Zian Wang, Wenzheng Chen, Zan Gojcic, Sanja Fidler, Nicholas Sharp^†, Jun Gao^† ACM Transactions on Graphics (SIGGRAPH), 2023 project page / pdf / supp / code / bibtex
	Neural Fields meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes Zian Wang, Tianchang Shen, Jun Gao, Shengyu Huang, Jacob Munkberg, Jon Hasselgren, Zan Gojcic, Wenzheng Chen, Sanja Fidler CVPR, 2023 project page / pdf / video / bibtex 🚢 Combined with other NVIDIA technology, FEGR is one component of Neural Reconstruction Engine announced in GTC Sept 2022 Keynote.
	GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images Jun Gao, Tianchang Shen, Zian Wang, Wenzheng Chen, Kangxue Yin, Daiqing Li, Or Litany, Zan Gojcic, Sanja Fidler NeurIPS, 2022 (Spotlight Presentation) project page / pdf / code / bibtex / two-minute papers
	Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion Zian Wang, Wenzheng Chen, David Acuna, Jan Kautz, Sanja Fidler ECCV, 2022 project page / pdf / video / bibtex
	DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer Wenzheng Chen, Joey Litalien, Jun Gao, Zian Wang, Clement Fuji Tsang, Sameh Khamis, Or Litany, Sanja Fidler NeurIPS, 2021 project page / pdf / bibtex
	Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting Zian Wang, Jonah Philion, Sanja Fidler, Jan Kautz ICCV, 2021 (Oral Presentation) project page / pdf / video / bibtex
	Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid Jun Gao, Zian Wang, Jinchen Xuan, Sanja Fidler ECCV, 2020 project page / pdf / presentation video (short, long) / bibtex
	Object Instance Annotation with Deep Extreme Level Set Evolution Zian Wang, David Acuna, Huan Ling, Amlan Kar, Sanja Fidler CVPR, 2019 project page / pdf / code / poster / bibtex Visit this page for code access. For research purpose signed up with an academic email, the code is automatically sent within minutes. Feel free to reach out if any issue occurs.
	Learning Semantics-Preserving Attention and Contextual Interaction for Group Activity Recognition Yansong Tang, Jiwen Lu, Zian Wang, Ming Yang, Jie Zhou IEEE Transaction on Image Processing (TIP), 2019 pdf / supp
	Mining Semantics-Preserving Attention for Group Activity Recognition Yansong Tang, Zian Wang, Peiyang Li, Jiwen Lu, Ming Yang, Jie Zhou ACM Multimedia, 2018 (Oral Presentation) pdf / slides
	Multi-stream Deep Neural Networks for RGB-D Egocentric Action Recognition Yansong Tang, Zian Wang, Jiwen Lu, Jianjiang Feng, Jie Zhou IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2018 pdf / supp / dataset

Academic Services

Conference Reviewer: ICCV, CVPR, ECCV, NeurIPS, SIGGRAPH

Journal Reviewer: T-PAMI, TVCG

Teaching Assistant, CSC 420: Introduction to Image Understanding 19 Fall, 20 Summer, 20 Fall

Teaching Assistant, CSC 320: Introduction to Visual Computing 19-20 Winter

Honors and Awards

Outstanding Reviewer Award, ECCV 2024

Best Paper Award, SIGGRAPH Asia 2023

SenseTime Undergraduate Scholarship, 2018

National Scholarship, 2017

website template