4 papers
LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models
Mingyang Xie, Numair Khan, Tianfu Wang +8
Given a monocular video, the goal of video re-rendering is to generate views of the scene from a novel camera trajectory. Existing methods face two distinct challenges. Geometrical…
Can Hallucination Correction Improve Video-Language Alignment?
Lingjun Zhao, Mingyang Xie, Paola Cascante-Bonilla +2
Large Vision-Language Models often generate hallucinated content that is not grounded in its visual inputs. While prior work focuses on mitigating hallucinations, we instead explor…
Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation
Tianfu Wang, Mingyang Xie, Haoming Cai +2
Transparent surfaces, such as glass, create complex reflections that obscure images and challenge downstream computer vision applications. We introduce Flash-Split, a robust framew…
Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats
Mingyang Xie, Haoming Cai, Sachin Shah +4
We introduce a simple yet effective approach for separating transmitted and reflected light. Our key insight is that the powerful novel view synthesis capabilities provided by mode…