Hualie Jiang

Papers

Total Citations

H-Index

About

Hualie Jiang is a computer vision researcher whose work focuses on the intersection of depth estimation, stereo matching, and robotics perception. His most recognized contribution, DEFOM-Stereo, introduces a novel approach to stereo matching by leveraging depth foundation models — large-scale pretrained monocular depth estimation networks — to overcome longstanding challenges in binocular disparity estimation, particularly in occluded regions and textureless surfaces where traditional matching cues fail. By bridging monocular relative depth priors with metric stereo matching, Jiang's work represents a meaningful step forward in generalizable, robust 3D scene understanding. Published in 2025, DEFOM-Stereo has already accumulated over 19 citations, signaling rapid uptake within the computer vision community and reflecting its relevance to both academic research and practical robotics applications. Jiang's research addresses a fundamental bottleneck in autonomous systems — reliable metric depth perception — making his contributions particularly valuable to developers working on autonomous vehicles, robotic manipulation, and augmented reality. His ability to synthesize advances in foundation models with classical geometric vision problems marks him as a promising and innovative voice in modern 3D computer vision research.