Image Generation

Food Image Generation on Multi-Noun Categories WACV 2026 Forecast Then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers AAAI 2026 Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Diffusion Transformers CVPR 2026 FreLay: Frequency-aware Energy Function for Training-free Layout-to-Image Generation AAAI 2026 FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing CVPR 2026 Frequency-Aware Flow Matching for High-Quality Image Generation CVPR 2026 From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition CVPR 2026 From Scale to Speed: Adaptive Test-Time Scaling for Image Editing CVPR 2026 From Sketch to Fresco: Efficient Diffusion Transformer with Progressive Resolution CVPR 2026 Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models WACV 2026 FutureMorph: Toward Predicting Future Deformation Fields in Longitudinal Imaging MIDL 2026 FVAR: Next-Focus Prediction for Visual Autoregressive Modeling CVPR 2026 Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers CVPR 2026 Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian Splatting AAAI 2026 GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting WACV 2026 GDRO: Group-level Reward Post-training Suitable for Diffusion Models CVPR 2026 Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy WACV 2026 GenColorBench: A Color Evaluation Benchmark for Text-to-Image Generation CVPR 2026 GenErase: Generalizable and Semantically-Aware Concept Erasure in Diffusion Models CVPR 2026 Generating Sketches in a Hierarchical Auto-Regressive Process for Flexible Sketch Drawing Manipulation at Stroke-Level AAAI 2026 Geo2: Geometry-Guided Cross-view Geo-Localization and Image Synthesis CVPR 2026 GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis CVPR 2026 GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding CVPR 2026 GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers CVPR 2026 GeoRK2: Geometry-Guided Runge-Kutta Integration for Diffusion Transformer Acceleration CVPR 2026