paper-conference

Video diffusion models have achieved impressive realism and controllability but are limited by high computational demands, restricting …

Recent progress in diffusion-based video editing has shown remarkable potential for practical applications. However, these methods …

Generative models have become a powerful tool for image editing tasks, including object insertion. However, these methods often lack …

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and …

This work aims to improve the efficiency of text-to-image diffusion models. While diffusion models use computationally expensive …

Novel View Synthesis (NVS), which tries to produce a realistic image at the target view given source view images and their …

This paper accelerates video perception, such as semantic segmentation and human pose estimation, by levering cross-frame redundancies. …

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention …

This paper aims to accelerate video stream processing, such as object detection and semantic segmentation, by leveraging the temporal …

High-resolution images are widely adopted for high-performance object detection in videos. However, processing high-resolution inputs …