Varun Jampani - Home (original) (raw)
I am VP Research at Stability AI, leading the generative vision research on image, video and 3D foundation models. In the past, I was a researcher at Google Research and Nvidia Research. I completed my PhD at Perceiving Systems department, Max-Planck Institute (MPI) for Intelligent Systems in Tübingen, Germany. My PhD advisor was Prof. Peter V. Gehler. I did my bachelors and masters in Computer Science at IIIT-Hyderabad, India.
At Stability AI, we strive to advance the state-of-the-art in vision foundation models with diverse applications in understanding, reconstruction and generation tasks in both 2D and 3D. A central research question is how to train generative models that can act as generic yet powerful priors for the visual world around us.
If you are interested in joining my Generative Vision team at Stability or research collaborations or internships, please drop me an email with your CV.
News
February, 2025 :Papers on ‘Stable Video 4D’ and ‘Monst3r to estimate geometry of dynamic scenes’ accepted to ICLR’25.
February, 2025 :Area chairing for ICCV’25 and NeurIPS’25.
July, 2024 :Papers on ‘Stable Video 3D’, ‘3D-Congealing’, ‘Zero-shot material transfer’, ‘stylized human motion diffusion’, ‘ZipLoRA for merging style LoRAs’, ‘Text generation of 3D garments’, ‘Joint 2D-3D pretraining from multi-view images’ accepted to ECCV’24.
July, 2024 :Area chairing for CVPR’25
May, 2024 :Area chairing for BMVC’24 and NeurIPS’24.
March, 2024 :Papers on ‘3D awareness in foundation models’, ‘Multi-view diffusion’, ‘One-shot affordance learning’, ‘Neural BRDF decomposition’, ‘DiffusionLight’, ‘Shape Regression’, ‘NeRF Inpainting’, ‘Diffusion material control’, ‘Joint image generation and segmentation’, ‘Geometric semantic correspondences’, ‘HyperDreamBooth’ accepted to CVPR’24.
January, 2024 :A paper on ‘Controllable human motion generation’ accepted to ICLR’24.
January, 2024 :Area chairing for ICML’24 and ECCV’24.
November, 2023 :Joined Stability AI as a research lead.