Image Editing

MedEBench: Diagnosing Reliability in Text-Guided Medical Image Editing EMNLP 2025 MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis CVPR 2025 MikuDance: Animating Character Art with Mixed Motion Dynamics ICCV 2025 MindPainter: Efficient Brain-Conditioned Painting of Natural Images via Cross-Modal Self-Supervised Learning AAAI 2025 MoEdit: On Learning Quantity Perception for Multi-object Image Editing CVPR 2025 Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing AAAI 2025 MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane Representation ICLR 2025 MTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting CVPR 2025 Multi-focal Conditioned Latent Diffusion for Person Image Synthesis CVPR 2025 MV-VTON: Multi-View Virtual Try-On with Diffusion Models AAAI 2025 Negative-Prompt Inversion: Fast Image Inversion for Editing with Text-Guided Diffusion Models WACV 2025 Neural Solver of Dichromatic Reflection Model for Specular Highlight Removal ICCV 2025 Non-Cross Diffusion for Semantic Consistency WACV 2025 NTClick: Achieving Precise Interactive Segmentation With Noise-tolerant Clicks CVPR 2025 ObjectMover: Generative Object Movement with Video Prior CVPR 2025 OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision ICLR 2025 OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking CVPR 2025 OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting ICCV 2025 ORIDa: Object-centric Real-world Image Composition Dataset CVPR 2025 Paint by Inpaint: Learning to Add Image Objects by Removing Them First CVPR 2025 Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion Models ICCV 2025 Pathways on the Image Manifold: Image Editing via Video Generation CVPR 2025 Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy CVPR 2025 Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation ICCV 2025 Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories CVPR 2025