Enver Sangineto

Papers

Total Citations

H-Index

About

Enver Sangineto is a leading researcher in computer vision and machine learning, with a primary focus on articulated object recognition, 3D scene understanding, and generative models. His foundational work introduced a general-purpose framework for recognizing articulated objects by decomposing them into rigid components, a methodology that has influenced subsequent research in deformable and part-based object detection. While his early contributions to articulated object recognition garnered modest initial citations, his more recent impact is substantial, with his work on neural rendering, image synthesis, and 3D reconstruction from single images accumulating thousands of citations. Sangineto is particularly known for advancing techniques that bridge the gap between 2D visual data and 3D structural reasoning, including notable contributions to self-supervised learning and generative adversarial networks. His research has been published in top-tier venues such as CVPR, ICCV, and ECCV, and he has served as an area chair for these conferences. Sangineto’s work is widely cited for its practical applications in robotics, augmented reality, and autonomous systems, making him a key figure in modern computer vision research.