EgoGen: An Egocentric Synthetic Data Generator
Gen Li, Kaifeng Zhao, Siwei Zhang, Xiaozhong Lyu, Mihai Dusmanu, Yan Zhang, Marc Pollefeys, Siyu Tang
Abstract
https://ego-gen.github.io/ RGB RGB with Motion Blur Depth Surface Normal Segmentation Mask World Position Figure 1. EgoGen: a scalable synthetic data generation system for egocentric perception tasks, with rich multi-modal data and accurate annotations. We simulate camera rigs for head-mounted devices (HMDs) and render from the perspective of the camera wearer with various sensors. Top to bottom: middle and right camera sensors in the rig. Left to right: photo-realistic RGB image, RGB with simulated motion blur, depth map, surface normal, segmentation mask, and world position for fisheye cameras widely used in HMDs.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 3fc0d1a1-cce0-4518-824c-c44706759c7fCited by top-tier papers9
- EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric ViewsYuhang Yang, Wei Zhai, Chengfeng Wang, Chengjun Yu et al.NeurIPS 2024 · 31 citations
- EgoM2P: Egocentric Multimodal Multitask PretrainingGen Li, Yutong Chen, Yiqian Wu, Kaifeng Zhao et al.ICCV 2025 · 3 citations
- LookOut: Real-World Humanoid Egocentric NavigationBoxiao Pan, Adam W. Harley, Francis Engelmann, C. Karen Liu et al.ICCV 2025 · 2 citations
- VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and CollisionsMarko Mihajlovic, Siwei Zhang, Gen Li, Kaifeng Zhao et al.ICCV 2025 · 2 citations
- Primal: Physically Reactive and Interactive Motor Model for Avatar LearningYan Zhang, Yao Feng, Alpár Cseke, Nitin Saini et al.ICCV 2025 · 1 citation
Builds on36
- AMASS: Archive of Motion Capture As Surface ShapesNaureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll et al.ICCV 2019 · 1,784 citations
- Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the LoopNikos Kolotouros, Georgios Pavlakos, Michael J. Black, Kostas DaniilidisICCV 2019 · 1,139 citations
- Habitat 2.0: Training Home Assistants to Rearrange their HabitatAndrew Szot, Alexander Clegg, Eric Undersander, Erik Wijmans et al.NeurIPS 2021 · 826 citations
- Action-Conditioned 3D Human Motion Synthesis with Transformer VAEMathis Petrovich, Michael J. Black, Gül VarolICCV 2021 · 672 citations
- PARE: Part Attention Regressor for 3D Human Body EstimationMuhammed Kocabas, Chun-Hao P. Huang, Otmar Hilliges, Michael J. BlackICCV 2021 · 509 citations
Related papers
- UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and GenerationChaitanya Patel, Hiroki Nakamura, Yuta Kyuragi, Kazuki Kozuka et al.ICCV 2025 · 3 citations
- Ego-1K - A Large-Scale Multiview Video Dataset for Egocentric VisionJae Yong Lee, Daniel Scharstein, Akash Bapat, Hao Hu et al.CVPR 2026 · 2 citations
- xR-EgoPose: Egocentric 3D Human Pose From an HMD CameraDenis Tomè, Patrick Peluse, Lourdes Agapito, Hernán BadinoICCV 2019 · 140 citations
- EgoPoseVR: Spatiotemporal Multi-Modal Reasoning for Egocentric Full-Body Pose in Virtual RealityHaojie Cheng, Shaun Jing Heng Ong, Shaoyu Cai, Aiden Tat Yang Koh et al.IEEE VR 2026 · 1 citation
- EgoRenderer: Rendering Human Avatars from Egocentric Camera ImagesTao Hu, Kripasindhu Sarkar, Lingjie Liu, Matthias Zwicker et al.ICCV 2021 · 23 citations
