CVPR2024
EgoGen: An Egocentric Synthetic Data Generator
Gen Li, Kaifeng Zhao, Siwei Zhang, Xiaozhong Lyu, Mihai Dusmanu, Yan Zhang, Marc Pollefeys, Siyu Tang
摘要
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.