Diffusion Models

Realistic Face Reconstruction from Facial Embeddings via Diffusion Models AAAI 2026 Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning CVPR 2026 Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs CVPR 2026 Real-Time Novel-View Freehand Ultrasound Imaging via Point-Cloud Rendering and Diffusion-Bridge Completion MIDL 2026 RealUHR: Harnessing Patch-Cascade Flows for Photorealistic Ultra-High-Resolution Synthesis AAAI 2026 Reasoning Diffusion for Unpaired Test Time Out-of-distribution Text-Image to Video Generation CVPR 2026 ReBrain: Brain MRI Reconstruction from Sparse CT Slice via Retrieval-Augmented Diffusion WACV 2026 RebRL: Reinforcing Discrete Visual Diffusion Models with Rebalanced Timestep Credits CVPR 2026 ReCoFuse: Ultra-Robust Image Fusion via Restorative Multi-Modal Diffusion Reciprocal Coupling CVPR 2026 ReContraster: Making Your Posters Stand Out with Regional Contrast ACL 2026 ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver AAAI 2026 Rectified Noise: A Generative Model Using Positive-incentive Noise AAAI 2026 Rectifying Latent Space for Generative Single-Image Reflection Removal CVPR 2026 RecTok: Reconstruction Distillation along Rectified Flow CVPR 2026 Refacade: Editing Object with Given Reference Texture CVPR 2026 RefiDiff: Progressive Refinement Diffusion for Efficient Missing Data Imputation AAAI 2026 Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning CVPR 2026 Reflection Separation from a Single Image via Joint Latent Diffusion CVPR 2026 Refracting Reality: Generating Images with Realistic Transparent Objects CVPR 2026 RefTon: Reference person shot assist virtual Try-on CVPR 2026 ReGenHOI: Unifying Reconstruction and Generation for 3D Human-Object Interaction Understanding CVPR 2026 Region-Adaptive Sampling for Diffusion Transformers CVPR 2026 RegionRoute: Regional Style Transfer with Diffusion Model CVPR 2026 Regressor-guided Diffusion Model for De Novo Peptide Sequencing with Explicit Mass Control AAAI 2026 ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers CVPR 2026