5 papers
VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment
Tengjiao Yin, Jinglei Shi, Heng Guo +1
Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial drift, and depth violations in ge…
NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting
Zaiyan Yang, Xinpeng Liu, Heng Guo +3
We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features, in order to obtain an accurate and robus…
ShaRP: SHAllow-LayeR Pruning for Efficient Video Large Language Models
Yingjie Xia, Tao Liu, Jinglei Shi +4
Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration…
Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance
Wenjie Li, Jinglei Shi, Jin Han +2
Clean images are crucial for visual tasks such as small object detection, especially at high resolutions. However, real-world images are often degraded by adverse weather, and weat…
MUSE: Manipulating Unified Framework for Synthesizing Emotions in Images via Test-Time Optimization
Yingjie Xia, Xi Wang, Jinglei Shi +2
Images evoke emotions that profoundly influence perception, often prioritized over content. Current Image Emotional Synthesis (IES) approaches artificially separate generation and…