Bingyi Kang

Papers

Total Citations

H-Index

About

Bingyi Kang is a leading researcher in computer vision, with a focus on depth estimation, foundation models, and visual prompting. His most influential work, "Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation" (2025), introduces a groundbreaking paradigm that brings prompting into depth foundation models for the first time. By leveraging low-cost prompts, Kang’s method enables precise metric depth estimation at 4K resolution, significantly advancing the capabilities of vision foundation models. This work has quickly garnered attention, accumulating 15 citations shortly after publication, reflecting its immediate impact on the field. Kang’s contributions bridge the gap between language and vision models, demonstrating how prompting can unlock new levels of accuracy and resolution in depth perception. His research is pivotal for applications in autonomous driving, robotics, and augmented reality, where high-fidelity depth information is critical. Through his innovative approach, Kang has established himself as a key figure in pushing the boundaries of what foundation models can achieve in visual understanding.