Image Generation

2S-CEDiff: A Two-Stage Diffusion Framework for Generating High-Fidelity Contrast-Enhanced CT Images from Non-Contrast Scans WACV 2026 3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting WACV 2026 3D Space as a Scratchpad for Editable Text-to-Image Generation CVPR 2026 4D-Animal: Freely Reconstructing Animatable 3D Animals from Videos WACV 2026 ACID-Style: An Adaptive Condition Injection Diffusion Model for Arbitrary Style Transfer AAAI 2026 AdaptDiff: Adaptive Guidance in Diffusion Models for Diverse and Identity-Consistent Face Synthesis (Student Abstract) AAAI 2026 Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation CVPR 2026 Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion Generation CVPR 2026 Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration CVPR 2026 AEDR: Training-Free AI-Generated Image Attribution via Autoencoder Double-Reconstruction AAAI 2026 AEON: Adaptive Embedding Optimized Noise for Robust Watermarking in Diffusion Models WACV 2026 AesX: Enhance Your Images with Stunning Aesthetic Beauty ACL 2026 A Fast, Simple, and Flexible Scale Informative Feature Transform Module for Arbitrary Scale Image Super-Resolution WACV 2026 Agentic Retoucher for Text-To-Image Generation CVPR 2026 AHS: Adaptive Head Synthesis via Synthetic Data Augmentations CVPR 2026 AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation AAAI 2026 Align Images Before You Generate CVPR 2026 All-in-One Slider for Attribute Manipulation in Diffusion Models CVPR 2026 AnchorDS: Anchoring Dynamic Sources for Semantically Consistent Text-to-3D Generation AAAI 2026 Anchoring and Rescaling Attention for Semantically Coherent Inbetweening CVPR 2026 An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integration AAAI 2026 Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation AAAI 2026 Any2RSI: Controllable Remote Sensing Text-to-Image Generation via Any Control and Enriched Description AAAI 2026 Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation CVPR 2026 A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space CVPR 2026