4 papers
A Closed-Loop Multi-Agent Framework for Aerodynamics-Aware Automotive Styling Design
Xinyu Jin, Shengmao Yan, Qingtao Wang +3
The core challenge in automotive exterior design is balancing subjective aesthetics with objective aerodynamic performance while dramatically accelerating the development cycle. To…
Physics-Guided Motion Loss for Video Generation Model
Bowen Xue, Giuseppe Claudio Guarnera, Shuang Zhao +1
Current video diffusion models generate visually compelling content but often violate basic laws of physics, producing subtle artifacts like rubber-sheet deformations and inconsist…
PBR-Inspired Controllable Diffusion for Image Generation
Bowen Xue, Giuseppe Claudio Guarnera, Shuang Zhao +1
Despite recent advances in text-to-image generation, controlling geometric layout and PBR material properties in synthesized scenes remains challenging. We present a pipeline that…
ReflectanceFusion: Diffusion-based text to SVBRDF Generation
Bowen Xue, Giuseppe Claudio Guarnera, Shuang Zhao +1
We introduce Reflectance Diffusion, a new neural text-to-texture model capable of generating high-fidelity SVBRDF maps from textual descriptions. Our method leverages a tandem neur…