Haotong Lin

Papers

Total Citations

H-Index

About

Haotong Lin is a rising star in computer vision, whose research centers on advancing depth estimation and visual foundation models. His most notable contribution is pioneering the concept of prompting for metric depth estimation, introduced in his 2025 work "Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation." This paper, already garnering 15 citations, demonstrates a paradigm shift: by applying prompting techniques—typically used in language models—to depth foundation models, Lin enables accurate, high-resolution metric depth estimation from a single image using only a low-cost reference. This breakthrough dramatically reduces the need for expensive sensor data, making precise 3D perception more accessible. Lin’s work bridges the gap between foundation model flexibility and task-specific precision, with implications for autonomous driving, robotics, and augmented reality. His innovative approach to integrating prompting into visual tasks marks him as a key figure in the next generation of computer vision research, pushing the boundaries of what foundation models can achieve with minimal supervision.