image synthesis
Image synthesis is the process of generating new images using algorithms and models, such as Generative Adversarial Networks (GANs) or neural style transfer, based on existing images or specific input conditions.
- CAMILA: Context-Aware Masking for Image Editing with Language Alignment
- Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation
- Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modeling
- Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback
- GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion
- LuxDiT: Lighting Estimation with Video Diffusion Transformer
- Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation
- Plug-and-Play Context Feature Reuse for Efficient Masked Generation
- STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
- Salient Concept-Aware Generative Data Augmentation
- Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration
- Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution