Ali Mahdavi‐Amiri

Papers

Total Citations

H-Index

About

Ali Mahdavi‐Amiri is a leading researcher in computer vision and graphics, specializing in 3D shape analysis, multimodal learning, and the modeling of articulated objects. His major contributions address fundamental challenges in reconstructing and understanding real-world 3D data. Notably, his work on "Multimodal Shape Completion via Implicit Maximum Likelihood Estimation" (2022, 13 citations) introduces a novel framework that leverages implicit neural representations to complete partial 3D scans, overcoming issues like occlusion and sparsity that plague real-world sensor data. This approach has significant implications for robotics and autonomous systems, enabling more robust perception. Additionally, his comprehensive "Survey on Modeling of Human‐made Articulated Objects" (2025, 6 citations) provides a critical synthesis of techniques for understanding the shape and motion of objects with moving parts, bridging gaps between computer vision, graphics, and robotics. With a growing citation impact, Mahdavi‐Amiri’s work is shaping the next generation of 3D modeling tools, offering practical solutions for everything from virtual reality to automated manufacturing. His research stands out for its focus on multimodal integration and real-world applicability.