Aleksander Hołyński

Email / Google Scholar / Bio / CV

About me

I'm a professor at Columbia University, and I lead the team at Google DeepMind working on generative 3D and world models. Previously, I was a postdoctoral scholar at UC Berkeley (BAIR) with Alyosha Efros and Angjoo Kanazawa, and did my PhD at the University of Washington with Steve Seitz, Brian Curless, and Rick Szeliski.

All Projects Representative Generative 3D Video & World Models Reconstruction Image Generation Products Students

Ryan Tabrizi PhD student, Columbia University Previously UC Berkeley Homepage / Scholar
Jordan Lin PhD student, Columbia University Co-advised with Micah Goldblum · Previously UCLA Homepage / GitHub
Gemini Omni The Gemini Omni team and collaborators at Google DeepMind 2026 Web / Model card
Genie 3: A New Frontier for World Models The Genie team and collaborators at Google DeepMind 2025 Web
ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training Haian Jin, Rundi Wu, Tianyuan Zhang, Ruiqi Gao, Jonathan T. Barron, Noah Snavely, Aleksander Holynski CVPR 2026 PDF / arXiv / Webpage / Code
VLIC: Vision-Language Models as Perceptual Judges for Human-Aligned Image Compression Kyle Sargent, Ruiqi Gao, Philipp Henzler, Charles Herrmann, Aleksander Holynski, Li Fei-Fei, Jiajun Wu, Jason Zhang CVPR 2026 PDF / arXiv / Webpage
Constantly Improving Image Models Need Constantly Improving Benchmarks Jiaxin Ge, Grace Luo, Heekyung Lee, Nishant Malpani, Long Lian, XuDong Wang, Aleksander Holynski, Trevor Darrell, Sewon Min, David M. Chan ICLR 2026 PDF / arXiv / Webpage
Veo 3 The Veo team and collaborators at Google DeepMind Web
Neural USD: An Object-Centric Framework for Iterative Editing and Control Alejandro Escontrela, Shrinu Kushagra, Sjoerd van Steenkiste, Yulia Rubanova, Aleksander Holynski, Kelsey Allen, Kevin Murphy, Thomas Kipf arXiv 2025 PDF / arXiv / Webpage
How Animals Dance (When You're Not Looking) Xiaojuan Wang, Aleksander Holynski, Brian Curless, Ira Kemelmacher, Steve Seitz arXiv 2025 PDF / arXiv / Webpage
Dual-Process Image Generation Grace Luo, Jonathan Granskog, Aleksander Holynski, Trevor Darrell ICCV 2025 PDF / arXiv
Bolt3D: Generating 3D Scenes in Seconds Stanislaw Szymanowicz, Jason Y. Zhang, Pratul Srinivasan, Ruiqi Gao, Arthur Brussee, Aleksander Holynski, Ricardo Martin-Brualla, Jonathan T. Barron, Philipp Henzler ICCV 2025 PDF / arXiv
Veo 2 The Veo team and collaborators at Google DeepMind Web
360° Product Spins on Google Search Google Research, Google Shopping, and collaborators 2024 Web
Continuous 3D Perception Model with Persistent State Qianqian Wang, Yifei Zhang, Aleksander Holynski, Alexei Efros, Angjoo Kanazawa CVPR 2025 (Oral Presentation) PDF / arXiv
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos Linyi Jin, Richard Tucker, Zhengqi Li, David Fouhey, Noah Snavely, Aleksander Holynski CVPR 2025 (Oral Presentation**) PDF / arXiv
CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models Rundi Wu, Ruiqi Gao, Ben Poole, Alex Trevithick, Changxi Zheng, Jon Barron, Aleksander Holynski CVPR 2025 (Oral Presentation) PDF / arXiv
MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos Zhengqi Li, Richard Tucker, Forrester Cole, Qianqian Wang, Linyi Jin, Vickie Ye, Angjoo Kanazawa, Aleksander Holynski, Noah Snavely CVPR 2025 (Oral, Best Paper Honorable Mention) PDF / arXiv
GPS as a Control Signal for Image Generation Chao Feng, Ziyang Chen, Aleksander Holynski, Alexei Efros, Andrew Owens CVPR 2025 PDF / arXiv
SimVS: Simulating World Inconsistencies for Robust View Synthesis Alex Trevithick, Roni Paiss, Philipp Henzler, Dor Verbin, Rundi Wu, Hadi Alzayer, Ruiqi Gao, Ben Poole, Jon Barron, Aleksander Holynski, Ravi Ramamoorthi, Pratul Srinivasan CVPR 2025 PDF / arXiv
Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation Xiaojuan Wang, Boyang Zhou, Brian Curless, Ira Kemelmacher, Aleksander Holynski, Steve Seitz ICLR 2025 PDF / arXiv
Rethinking Score Distillation as a Bridge Between Image Distributions David McAllister, Songwei Ge, Jia-Bin Huang, David W. Jacobs, Alexei A. Efros, Aleksander Holynski, Angjoo Kanazawa NeurIPS 2024 PDF / arXiv
Diffusion Models as Data Mining Tools Ioannis Siglidis, Aleksander Holynski, Alexei Efros, Mathieu Aubry, Shiry Ginosar ECCV 2024 (Spotlight) PDF / arXiv
VidPanos: Generative Panoramic Videos from Casual Panning Videos Jingwei Ma, Erika Lu, Roni Paiss, Shiran Zada, Aleksander Holynski, Tali Dekel, Brian Curless, Michael Rubinstein, Forrester Cole SIGGRAPH Asia 2024 PDF / arXiv
CAT3D: Create Anything in 3D with Multi-View Diffusion Models Ruiqi Gao, Aleksander Holynski, Philipp Henzler, Arthur Brussee, Ricardo Martin-Brualla, Pratul Srinivasan, Jon Barron, Ben Poole* NeurIPS 2024 (Oral Presentation) PDF / arXiv
Disentangled 3D Scene Generation with Layout Learning Dave Epstein, Ben Poole, Ben Mildenhall, Alexei Efros, Aleksander Holynski ICML 2024 PDF / arXiv
Generative Image Dynamics Zhengqi Li, Richard Tucker, Noah Snavely, Aleksander Holynski CVPR 2024 (Oral, Best Paper Award) PDF / Webpage
Readout Guidance: Learning Control from Diffusion Features Grace Luo, Trevor Darrell, Oliver Wang, Dan B Goldman, Aleksander Holynski CVPR 2024 (Highlight) PDF / arXiv
ReconFusion: 3D Reconstruction with Diffusion Priors Rundi Wu, Ben Mildenhall, Philipp Henzler, Keunhong Park, Ruiqi Gao, Daniel Watson, Pratul Srinivasan, Dor Verbin, Jon Barron, Ben Poole, Aleksander Holynski* CVPR 2024 PDF / arXiv
Generative Powers of Ten Xiaojuan Wang, Janne Kontkanen, Brian Curless, Steve Seitz, Ira Kemelmacher, Ben Mildenhall, Pratul Srinivasan, Dor Verbin, Aleksander Holynski CVPR 2024 (Highlight) PDF / arXiv
Video Interpolation with Diffusion Models Siddhant Jain, Daniel Watson, Eric Tabellion, Aleksander Holynski, Ben Poole, Janne Kontkanen CVPR 2024 PDF / arXiv
NeRFiller: Completing Scenes via Generative 3D Inpainting Ethan Weber, Aleksander Holynski, Varun Jampani, Saurabh Saxena, Noah Snavely, Abhishek Kar, Angjoo Kanazawa CVPR 2024 PDF / arXiv
Infinite Texture: Text-guided High Resolution Diffusion Texture Synthesis Yifan Wang, Aleksander Holynski, Brian Curless, Steve Seitz arXiv 2024 PDF / arXiv
ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models Meng-Li Shih, Wei-Chiu Ma, Lorenzo Boyice, Aleksander Holynski, Forrester Cole, Brian Curless, Janne Kontkanen CVPR 2024 PDF / arXiv / Webpage
RealFill: Reference-Driven Generation for Authentic Image Completion Luming Tang, Nataniel Ruiz, Qinghao Chu, Yuanzhen Li, Aleksander Holynski, David E. Jacobs, Bharath Hariharan, Yael Pritch, Neal Wadhwa, Kfir Aberman, Michael Rubinstein SIGGRAPH 2024 PDF / Webpage
State of the Art on Diffusion Models for Visual Computing Ryan Po, Wang Yifan, Vladislav Golyanik, Kfir Aberman, Jon Barron, Amit Bermano, Eric Ryan Chan, Tali Dekel, Aleksander Holynski, Angjoo Kanazawa, C. Karen Liu, Lingjie Liu, Ben Mildenhall, Matthias Niessner, Bjorn Ommer, Christian Theobalt, Peter Wonka, Gordon Wetzstein Eurographics 2024 PDF / arXiv
Tracking Everything Everywhere All at Once Qianqian Wang, Yen-Yu Chang, Ruojin Cai, Zhengqi Li, Bharath Hariharan, Aleksander Holynski, Noah Snavely ICCV 2023 (Oral, Best Student Paper Award) PDF / Webpage
Diffusion Self-Guidance for Controllable Image Generation Dave Epstein, Allan Jabri, Ben Poole, Alexei A. Efros, Aleksander Holynski NeurIPS 2023 PDF / Webpage
Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence Grace Luo, Lisa Dunlap, Seth Dong Huk Park, Aleksander Holynski, Trevor Darrell NeurIPS 2023 PDF / Webpage / Code
Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions Ayaan Haque, Matthew Tancik, Alexei A. Efros, Aleksander Holynski, Angjoo Kanazawa ICCV 2023 (Oral Presentation) PDF / Webpage
Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs Frederik Warburg, Ethan Weber, Matt Tancik, Aleksander Holynski, Angjoo Kanazawa ICCV 2023 PDF / Webpage
DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion Johanna Karras, Aleksander Holynski, Ting-Chun Wang, Ira Kemelmacher ICCV 2023 PDF / Webpage
InstructPix2Pix: Learning to Follow Image Editing Instructions Tim Brooks, Aleksander Holynski, Alexei A. Efros CVPR 2023 (Highlight) PDF / Webpage / Code
SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage Yifan Wang, Aleksander Holynski, Xiuming Zhang, Cecilia Zhang CVPR 2023 PDF / Webpage / Video
Animating Pictures with Eulerian Motion Fields Aleksander Holynski, Brian Curless, Steven M. Seitz, Richard Szeliski CVPR 2021 (Oral Presentation) PDF / Webpage / Video Press: (Two Minute Papers), (Gizmodo)
Reducing Drift in Structure From Motion Using Extended Features Aleksander Holynski, David Geraghty, Jan-Michael Frahm, Chris Sweeney, Richard Szeliski 3DV 2020 (Oral Presentation) PDF / Webpage / Video
Seeing the World in a Bag of Chips Jeong Joon Park, Aleksander Holynski, Steve Seitz CVPR 2020 (Oral Presentation) PDF / Webpage / Talk / Supplementary Press: (Wired), (Scientific American)
Fast Depth Densification for Occlusion-aware Augmented Reality Aleksander Holynski, Johannes Kopf SIGGRAPH Asia 2018 PDF / Code / Webpage / Video Press: (FB Research in Brief)
Structure from Motion for Panorama-Style Videos Chris Sweeney, Aleksander Holynski, Brian Curless, Steve Seitz arXiv preprint 2018 PDF
Holoscanner: Gamified 3D Scanning Aleksander Holynski, and collaborators at the University of Washington 2016 Webpage / Video

@article{Occlusion2018,
  author    = {Aleksander Holynski and Johannes Kopf},
  title     = {Fast Depth Densification for Occlusion-aware Augmented Reality},
  booktitle = {ACM Transactions on Graphics (Proc. SIGGRAPH Asia)},
  publisher = {ACM},
  volume = {37},
  number = {6},
  year = {2018}}