Wenqi Dong — accepted AI-conference papers

2025

InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes

Zesong Yang, Bangbang Yang, Wenqi Dong, Chenxuan Cao, Liyuan Cui, Yuewen Ma +2

ICCV 2025poster

Humans can naturally identify and mentally complete occluded objects in cluttered environments. However, imparting similar cognitive ability to robotics remains challenging even with advanced reconstruction techniques, which models scenes as undifferentiated wholes and fails to recognize complete ob…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

DELTAR: Depth Estimation from a Light-Weight ToF Sensor and RGB Image

Yijin Li, Xinyang Liu, Wenqi Dong, Han Zhou, Hujun Bao, Guofeng Zhang +2

ECCV 2022poster

"Light-weight time-of-flight (ToF) depth sensors are small, cheap, low-energy and have been massively deployed on mobile devices for the purposes like autofocus, obstacle detection, etc. However, due to their specific measurements (depth distribution in a region instead of the depth value at a certa…

Cited by 31 Source ↗PDF ↗code ↗Scholar ↗