Chengyi Zeng
Papers
1
Total Citations
6
H-Index
1
About
Chengyi Zeng is a researcher focused on advancing computer vision through efficient deep learning, with a particular emphasis on self-supervised methods for monocular depth estimation. Their most cited work, "Self-supervised learning of monocular depth using quantized networks" (2021), introduces a novel approach that leverages network quantization to reduce computational overhead while maintaining high accuracy in depth prediction from single images. This contribution is significant for deploying depth estimation models on resource-constrained devices, such as mobile robots or augmented reality systems, without relying on costly labeled data. With 6 citations, this paper has already garnered attention for bridging the gap between model efficiency and self-supervised learning—a critical challenge in modern vision research. Zeng’s work exemplifies a practical, impactful direction in making advanced computer vision techniques more accessible and deployable, positioning them as a promising voice in the field of efficient deep learning and 3D scene understanding.
Research Focus
Key Achievements
Top Papers
- 1Self-supervised learning of monocular depth using quantized networks6 citations · 2021