Junlin Han

Papers

Total Citations

H-Index

About

Junlin Han is an emerging researcher specializing in 3D computer vision, with a particular focus on multi-view stereo (MVS) and learning-based 3D reconstruction techniques. His work sits at the intersection of deep learning and geometric vision, addressing fundamental challenges in recovering dense 3D structures from multi-view imagery — a capability critical to real-world applications including augmented and virtual reality, autonomous driving, and robotics. Han's most notable contribution to date is his comprehensive survey on learning-based multi-view stereo (2024), which systematically synthesizes the rapidly evolving landscape of deep learning approaches to MVS algorithms. By consolidating methodologies, benchmarks, and open challenges in this domain, the work serves as a valuable reference for both newcomers and seasoned researchers navigating this complex field. Though early in its citation trajectory with 2 citations since publication, survey papers of this nature typically accumulate significant influence over time as the community references them for context and direction. Han's research reflects a broader trend of leveraging machine learning to overcome the limitations of classical geometric reconstruction pipelines, positioning him as a contributor to one of computer vision's most practically impactful frontiers.