10 papers · 1 filter
VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel Optimization
Jiajing Lin, Shu Jiang, Qingyuan Zeng +2
The intrinsic dynamics of an object governs its physical behavior in the real world, playing a critical role in enabling physically plausible interactive simulation with 3D assets.…
A Theory-Inspired Framework for Few-Shot Cross-Modal Sketch Person Re-Identification
Yunpeng Gong, Yongjie Hou, Jiangming Shi +2
Sketch based person re-identification aims to match hand-drawn sketches with RGB surveillance images, but remains challenging due to significant modality gaps and limited annotated…
Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition Perception
Jiajing Lin, Zhenzhong Wang, Dejun Xu +3
4D content generation aims to create dynamically evolving 3D content that responds to specific input objects such as images or 3D representations. Current approaches typically inco…
Cross-Modality Perturbation Synergy Attack for Person Re-identification
Yunpeng Gong, Zhun Zhong, Yansong Qu +3
In recent years, there has been significant research focusing on addressing security concerns in single-modal person re-identification (ReID) systems that are based on RGB images.…
NexusSplats: Efficient 3D Gaussian Splatting in the Wild
Yuzhou Tang, Dejun Xu, Yongjie Hou +2
Photorealistic 3D reconstruction of unstructured real-world scenes remains challenging due to complex illumination variations and transient occlusions. Existing methods based on Ne…
Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimization
Yunpeng Gong, Qingyuan Zeng, Dejun Xu +2
In recent years, despite significant advancements in adversarial attack research, the security challenges in cross-modal scenarios, such as the transferability of adversarial attac…