Diffusion Models

Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing CVPR 2025 Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities ICML 2025 UP-Restorer: When Unrolling Meets Prompts for Unified Image Restoration AAAI 2025 Using Diffusion Priors for Video Amodal Segmentation CVPR 2025 Using Powerful Prior Knowledge of Diffusion Model in Deep Unfolding Networks for Image Compressive Sensing CVPR 2025 USP: Unified Self-Supervised Pretraining for Image Generation and Understanding ICCV 2025 VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction COLING 2025 VAFlow: Video-to-Audio Generation with Cross-Modality Flow Matching ICCV 2025 VaLID: Variable-Length Input Diffusion for Novel View Synthesis WACV 2025 Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion Models ICML 2025 Variational Control for Guidance in Diffusion Models ICML 2025 Variational Diffusion Posterior Sampling with Midpoint Guidance ICLR 2025 Variational Schrödinger Momentum Diffusion AISTATS 2025 VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis CVPR 2025 VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control ICLR 2025 VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning ICLR 2025 VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation ICCV 2025 VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness CVPR 2025 VersaFusion: A Versatile Diffusion-Based Framework for Fine-Grained Image Editing and Enhancement AAAI 2025 VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis AAAI 2025 Versatile Transition Generation with Image-to-Video Diffusion ICCV 2025 ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler ICLR 2025 ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis ICCV 2025 VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation CVPR 2025 Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localization ICCV 2025