Yuxuan Xue

Papers

Total Citations

H-Index

About

Yuxuan Xue is a rising researcher at the forefront of 3D computer vision and human-scene interaction, whose work bridges the gap between single-image understanding and physically plausible 3D reconstruction. Her key research areas include human-scene interaction modeling, physically consistent 3D reconstruction, and contact reasoning from monocular imagery. Xue's most notable contribution is the development of PhySIC, a groundbreaking framework that reconstructs metrically accurate humans and their surrounding scenes from a single image—addressing long-standing challenges of depth ambiguity, occlusions, and physically inconsistent contacts. This work, published in 2025, has already garnered 2 citations, signaling its immediate impact on the field. By enforcing physical plausibility in human-scene interactions, Xue's research has critical implications for virtual reality, robotics, and comprehensive 3D scene understanding. Her approach represents a significant advance over existing methods that struggle with realistic contact modeling, offering a pathway toward more immersive and physically grounded digital environments. As an emerging voice in computer vision, Xue's work promises to shape how machines perceive and interact with complex 3D spaces.