Jiaqi Han
Papers
1
Total Citations
3
H-Index
1
About
Jiaqi Han is a rising researcher at the forefront of 3D computer vision and geometric deep learning, with a focus on bridging the gap between unstructured visual data and structured parametric models. Their most prominent work, "Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization" (2024, 3 citations), tackles the challenging problem of converting a single image into a fully editable CAD model. This contribution is significant because it leverages vision-language models (VLMs) to factorize the reverse engineering process, enabling the extraction of discrete, parametric primitives from continuous image data—a task that has long been hindered by the representational mismatch between rasterized images and CAD's geometric primitives. By introducing a conditional factorization framework, Han's work opens new possibilities for interactive editing, manufacturing, and robotics, where editable 3D models are essential. Though early in its citation lifecycle, this paper has already garnered attention for its novel approach to a long-standing problem. Han's research sits at the intersection of computer vision, computer graphics, and AI, promising to democratize 3D content creation and accelerate workflows in design and engineering.
Research Focus
Key Achievements
Top Papers
- 1