5 papers
Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions
Xiaoxiao Sun, Mingyang Li, Kun Yuan +7
Large Vision-Language Models (VLMs) often answer classic visual illusions "correctly" on original images, yet persist with the same responses when illusion factors are inverted, ev…
UniMGS: Unifying Mesh and 3D Gaussian Splatting with Single-Pass Rasterization and Proxy-Based Deformation
Zeyu Xiao, Mingyang Sun, Yimin Cong +7
Joint rendering and deformation of mesh and 3D Gaussian Splatting (3DGS) have significant value as both representa tions offer complementary advantages for graphics applica tions.…
Continuous Perception Matters: Diagnosing Temporal Integration Failures in Multimodal Models
Zeyu Wang, Zhenzhen Weng, Serena Yeung-Levy
Continuous perception, the ability to integrate visual observations over time in a continuous stream fashion, is essential for robust real-world understanding, yet remains largely…
Temporal Preference Optimization for Long-Form Video Understanding
Rui Li, Xiaohan Wang, Yuhui Zhang +3
Despite significant advancements in video large multimodal models (video-LMMs), achieving effective temporal grounding in long-form videos remains a challenge for existing models.…
DeforHMR: Vision Transformer with Deformable Cross-Attention for 3D Human Mesh Recovery
Jaewoo Heo, George Hu, Zeyu Wang +1
Human Mesh Recovery (HMR) is an important yet challenging problem with applications across various domains including motion capture, augmented reality, and biomechanics. Accurately…