5 papers · 1 filter
PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
Yuanhao Cai, Kunpeng Li, Menglin Jia +11
Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws remains an open challenge. Existin…
Synthesizing Artifact Dataset for Pixel-level Detection
Dennis Menn, Feng Liang, Diana Marculescu
Artifact detectors have been shown to enhance the performance of image-generative models by serving as reward models during fine-tuning. These detectors enable the generative model…
Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility
Yiheng Li, Feng Liang, Dan Kondratyuk +3
The substantial training cost of diffusion models hinders their deployment. Immiscible Diffusion recently showed that reducing diffusion trajectory mixing in the noise space via li…
Similarity Trajectories: Linking Sampling Process to Artifacts in Diffusion-Generated Images
Dennis Menn, Feng Liang, Hung-Yueh Chiang +1
Artifact detection algorithms are crucial to correcting the output generated by diffusion models. However, because of the variety of artifact forms, existing methods require substa…
Looking Backward: Streaming Video-to-Video Translation with Feature Banks
Feng Liang, Akio Kodaira, Chenfeng Xu +3
This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video (V2V) translation with user prompts. Unlike prior V2V methods using batches to p…