Diffusion Models

Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model WACV 2026 No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation CVPR 2026 NS-Diff: Fluid Navier-Stokes Guided Video Diffusion via Reinforcement Learning CVPR 2026 ObjectAdv: Object-Level Unrestricted Adversarial Attacks via Diffusion Models AAAI 2026 Object Fusion via Diffusion Time-step for Customized Image Editing with Single Example AAAI 2026 ObjectMorpher: 3D-Aware Image Editing via Deformable 3DGS CVPR 2026 Object-WIPER: Training-Free Object and Associated Effect Removal in Videos CVPR 2026 Occluded Human Body Capture with Frequency Domain Denoising Prior CVPR 2026 ODEt(ODEl): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling WACV 2026 O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing AAAI 2026 Odo: Depth-Guided Diffusion for Identity-Preserving Body Reshaping WACV 2026 Olbedo: An Albedo and Shading Aerial Dataset for Large-Scale Outdoor Environments CVPR 2026 OMGTex: One-stage Multi-style Facial Texture Reconstruction without Geometry Guidance CVPR 2026 Omni2Sound: Towards Unified Video-Text-to-Audio Generation CVPR 2026 OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text CVPR 2026 Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning CVPR 2026 OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding AAAI 2026 One Algorithm to Align Them All CVPR 2026 OneHOI: Unifying Human-Object Interaction Generation and Editing CVPR 2026 One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers CVPR 2026 One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion AAAI 2026 One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution CVPR 2026 One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer CVPR 2026 One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control CVPR 2026 OntoAug: Rethinking Generative Data Augmentation via Ontology Guidance CVPR 2026