Ayush Saraf

I am a Staff Software Engineer at Meta Reality Labs in New York, where I work on Hyperscape and 3D world generation. I build creative tools that help people create 3D worlds—whether capturing real spaces or imagining entirely new ones.

Email  /  Google Scholar  /  Twitter  /  Github

profile photo

Hyperscape

Meta Horizon Hyperscape
Ayush Saraf (Tech Lead)
Launched at Meta Connect, September 2025  

Hyperscape lets you scan real-world spaces with a Quest headset and explore them in VR with photorealistic quality. The technology uses Gaussian splatting to recreate physical environments in virtual reality. As Tech Lead from the start, I led development of the core Gaussian splatting pipeline, tooling, and research infrastructure.

Reviews & Coverage

Press: TechCrunch / CNET / UploadVR / The Ghost Howls / Gizmodo

Research

I'm interested in machine learning, computer vision, computer graphics, 3D reconstruction and GenAI. Much of my research revolves around creating 3D worlds by observing real world through images or by interpretting user's imagination via geneative models.

Textured Gaussians for Enhanced 3D Scene Appearance Modeling
Brian Chao, Hung-Yu Tseng, Lorenzo Porzi, Chen Gao, Tuotuo Li, Qinbo Li, Ayush Saraf, Jia-Bin Huang, Johannes Kopf, Gordon Wetzstein, Changil Kim
CVPR 2025
LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-time Rendering
Jaehoon Choi, Rajvi Shah, Qinbo Li, Yipeng Wang, Ayush Saraf, Changil Kim, Jia-Bin Huang, Dinesh Manocha, Suhib Alsisan, Johannes Kopf
CVPR 2024
OmnimatteRF: Robust Omnimatte with 3D Background Modeling
Geng Lin, Chen Gao, Jia-Bin Huang, Changil Kim, Yipeng Wang, Matthias Zwicker, Ayush Saraf
ICCV 2023
Robust Dynamic Radiance Fields
Yu-Lun Liu, Chen Gao, Andreas Meuleman, Hung-Yu Tseng, Ayush Saraf, Changil Kim, Yung-Yu Chuang, Johannes Kopf, Jia-Bin Huang
CVPR 2023
Boosting view synthesis with residual transfer
Boosting view synthesis with residual transfer
Xuejian Rong, Jia-Bin Huang, Ayush Saraf, Changil Kim, Johannes Kopf
CVPR 2022
Dynamic View Synthesis from Dynamic Monocular Video
Chen Gao, Ayush Saraf, Johannes Kopf, Jia-Bin Huang
ICCV 2021
AMICO: Amodal Instance Composition
AMICO: Amodal Instance Composition
Peiye Zhuang, Denis Demandolx, Ayush Saraf, Xuejian Rong, Changil Kim and Jia-Bin Huang
BMVC 2021
Flow-edge Guided Video Completion
Chen Gao, Ayush Saraf, Jia-Bin Huang, Johannes Kopf
ECCV 2020
One shot 3d photography
Johannes Kopf, Kevin Matzen, Suhib Alsisan, Ocean Quigley, Francis Ge, Yangming Chong, Josh Patterson, Jan-Michael Frahm, Shu Wu, Matthew Yu, Peizhao Zhang, Zijian He, Peter Vajda, Ayush Saraf, Michael F. Cohen
SIGGRAPH 2020

Miscellanea

Program Committe, XRNeRF CVPR 2023
Peer Reviewer, CVPR 2023
Peer Reviewer, ICCV 2023
Peer Reviewer, WACV 2023
Peer Reviewer, WACV 2024
Peer Reviewer, IJCV

Template from Jon Barron.