VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinementby Daeun Lee, Jaehong Yoon, Jaemin…
Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstructionby Jordan Vice,…
Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Studyby Xibo Sun, Jiarui Fang, Aoyu Li,…
SSEditor: Controllable Mask-to-Scene Generation with Diffusion Modelby Haowen Zheng, Yanyan LiangFirst submitted to arxiv on:…
SpatialDreamer: Self-supervised Stereo Video Synthesis from Monocular Inputby Zhen Lv, Yangqi Long, Congzhentao Huang, Cao…
Medical Video Generation for Disease Progression Simulationby Xu Cao, Kaizhao Liang, Kuei-Da Liao, Tianren Gao,…
CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesisby Yifan Xie,…
MetricGold: Leveraging Text-To-Image Latent Diffusion Models for Metric Depth Estimationby Ansh Shah, K Madhava KrishnaFirst…
Time Step Generating: A Universal Synthesized Deepfake Image Detectorby Ziyue Zeng, Haoyuan Liu, Dingjie Peng,…
ColorEdit: Training-free Image-Guided Color editing with diffusion modelby Xingxi Yin, Zhi Li, Jingfeng Zhang, Chenglin…