Lahav LipsonI am a final (5th) year PhD candidate in the Vision & Learning Lab at Princeton University, supervised by Prof. Jia Deng My research focuses on generating large-scale synthetic data and building deep networks for 3D vision that leverage strong assumptions about epipolar geometry to achieve better generalization and test accuracy. |
|
Research |
|
Multi-Session SLAM with Differentiable Wide-Baseline Pose OptimizationLahav Lipson and Jia Deng CVPR 2024 paper / code |
|
Infinigen Indoors: Photorealistic Indoor Scenes using Procedural GenerationAlexander Raistrick*, Lingjie Mei*, Karhan Kaan Kayan* (equal contribution) David Yan, Yiming Zuo, Beining Han, Hongyu Wen, Meenal Parakh, Stamatis Alexandropoulos, Lahav Lipson, Zeyu Ma, Jia Deng CVPR 2024 paper (coming soon) / code (coming soon) |
|
View-Dependent Octree-based Mesh Extraction in Unbounded Scenes for Procedural Synthetic DataZeyu Ma, Alexander Raistrick, Lahav Lipson, Jia Deng Arxiv 2023 paper / code (integrated into Infinigen) |
|
Infinigen: Infinite Photorealistic Worlds using Procedural GenerationLahav Lipson*, Alexander Raistrick*, Zeyu Ma* (* equal contribution), Lingjie Mei, Mingzhe Wang, Yiming Zuo, Karhan Kayan, Hongyu Wen, Beining Han, Yihan Wang, Alejandro Newell, Hei Law, Ankit Goyal, Kaiyu Yang, Jia Deng CVPR 2023 website / paper / video / code |
|
Deep Patch Visual OdometryZachary Teed*, Lahav Lipson* and Jia Deng (* equal contribution) Neurips 2023 paper / code |
Coupled Iterative Refinement for 6D Multi-Object Pose EstimationLahav Lipson, Zachary Teed, Ankit Goyal and Jia Deng CVPR 2022 paper / code / poster / video |
|
RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo MatchingLahav Lipson, Zachary Teed and Jia Deng 3DV 2021 (Best Student Paper) paper / code / poster |
|