Libing Zeng (曾立兵)

   

I am currently a Research Scientist on Interactive Perception team at PICO, ByteDance. I obtained my PhD in Computer Science from Texas A&M University, where I was fortunate to be advised by Dr. Nima Khademi Kalantari. I was a research intern at Netflix Eyeline Studios (Scanline VFX) (2024), and OPPO US Research Center (2022). I have had the privilege of working closely with Dr. Li-Yi Wei and Dr. Paul Debevec during my academic journey. I earned my bachelor's degree in Electronic Information Engineering from Hunan University where I worked with Dr. Shaoyuan Wang.

My research lies at the intersection of generative AI, 3D vision, computer graphics, and embodied intelligence. I develop neural rendering, reconstruction, and generative modeling methods that learn structured, controllable, and geometrically consistent representations from large-scale visual data. My work spans personalized visual modeling, controllable generation, and world models for prediction, simulation, and robot learning. Ultimately, I aim to build scalable models that can understand, reconstruct, generate, and simulate complex visual environments.

         
News
  • [05/2026] One first-authored paper accepted to EGSR 2026. New
  • [01/2026] I’m starting a new position as Research Scientist at ByteDance.
  • [04/2025] One co-authored paper accepted to CVPRW 2025.
  • [10/2024] One first-authored paper accepted to WACV 2025.
  • [01/2024] Incoming research intern collaborating with Dr. Paul Debevec at Eyeline Studios - Powered by Netflix.
  • [08/2023] One first-authored paper conditionally accepted to SIGGRAPH Asia 2023.
  • [07/2023] One co-authored paper accepted to ICCV 2023.
  • [02/2023] One first-authored paper accepted to CVPR 2023.
  • [12/2022] One first-authored paper accepted to CGF 2023 (Eurographics 2023).
  • [05/2021] One co-authored paper accepted to ICCP 2021.
Experience
  1. Research Scientist ByteDance Jan 2026 - Present. San Jose, California, United States. Worked on digital humans, controllable video generation, and human-centric world models.
  2. Research Assistant Texas A&M University Aug 2019 - Dec 2025 · 6 yrs 5 mos. College Station, Texas, United States. Conducted research in generative modeling, neural rendering, 3D vision, reconstruction, and personalized visual modeling.
  3. Research Intern Netflix Eyeline Studios (Scanline VFX) May 2024 - Aug 2024 · 4 mos. Los Angeles, California, United States. Worked on 3D face re-aging and controllable 3D avatar generation using 3D Gaussian Splatting and diffusion models.
  4. Research Intern OPPO US Research Center Jun 2022 - Nov 2022 · 6 mos. Palo Alto, California, United States. Developed methods for 3D-aware facial landmark detection and egocentric 3D hand-trajectory forecasting.
Publications
  1. ReAge3D: Re-Aging 3D Faces with View Consistency Libing Zeng, Li Ma, Mingming He, Ning Yu, Paul Debevec, Nima Khademi Kalantari. The 37th Eurographics Symposium on Rendering (EGSR 2026)
    [Abstract] [Paper] [Project]
  2. Text2Stereo: Repurposing Stable Diffusion for Stereo Generation with Consistency Rewards Aakash Garg, Libing Zeng, Andrii Tsarov, Nima Khademi Kalantari. The IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2025)
    [Abstract] [Paper] [Project]
  3. Analyzing and Improving the Skin Tone Consistency and Bias in Implicit 3D Relightable Face Generators Libing Zeng, Nima Khademi Kalantari. The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)
    [Abstract] [Paper] [Project]
  4. MyStyle++: A Controllable Personalized Generative Prior Libing Zeng, Lele Chen, Yi Xu, Nima Khademi Kalantari. SIGGRAPH Asia 2023
    [Abstract] [Paper] [Project]
  5. Uncertainty-aware State Space Transformer for Egocentric 3D Trajectory Forecasting Wentao Bao, Lele Chen, Libing Zeng, Zhong Li, Yi Xu, Junsong Yuan, Yu Kong. The International Conference on Computer Vision (ICCV 2023)
    [Abstract] [Paper] [Project]
  6. 3D-aware Facial Landmark Detection via Multiview Consistent Training on Synthetic Data Libing Zeng, Lele Chen, Wentao Bao, Zhong Li, Yi Xu, Junsong Yuan, Nima Khademi Kalantari. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2023)
    [Abstract] [Paper] [Project]
  7. Test-Time Optimization for Video Depth Estimation Using Pseudo Reference Depth Libing Zeng, Nima Khademi Kalantari. Computer Graphics Forum (CGF 2023) (Proceedings of Eurographics 2023)
    [Abstract] [Paper] [Project]
  8. Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask Avinash Paliwal, Libing Zeng, Nima Khademi Kalantari. International Conference on Computational Photography (ICCP 2021)
    [Abstract] [Paper] [Project] [ICCP Talk]
  9. Rectifying Proposal Failures in Metropolis Light Transport Libing Zeng, Li-Yi Wei. Preprint (HAL 2019)
    [Abstract] [Paper] [Code_pbrt] [Code_tungsten]
Projects (Prior to PhD)
  1. A Renderer Written from the Scratch (BART Animations with High-Frequency Textures) Supervised by Dr. Li-Yi Wei. Exercises
    [Abstract] [Project] [Animation_robot] [Animation_kitchen] [Animation_museum]
  2. A Renderer Extended from the Book, Ray Tracing from the Ground Up Self-study Exercises
    [Abstract] [Project]
  3. A Renderer with Implementations of Various NON-TRIANGULATE Surfaces Self-study Exercises
    [Abstract] [Project]
Teaching
Community Services
Awards