visual quality
A measure of the perceptual fidelity and realism of generated images or visual outputs in AI systems. It often encompasses sharpness, color accuracy, and overall aesthetic appeal, particularly in generative tasks.
- 1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
- A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
- AnimateQR: Bridging Aesthetics and Functionality in Dynamic QR Code Generation
- ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts
- ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts
- DIFFSSR: Stereo Image Super-resolution Using Differential Transformer
- DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
- FSI-Edit: Frequency and Stochasticity Injection for Flexible Diffusion-Based Image Editing
- FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering
- FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation
- Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals
- Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation
- Generative Model Inversion Through the Lens of the Manifold Hypothesis
- GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion
- HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance
- Improving Progressive Generation with Decomposable Flow Matching
- Mask Image Watermarking
- OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers
- Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
- Temporal In‑Context Fine‑Tuning for Versatile Control of Video Diffusion Models
- ViewCraft3D: High-fidelity and View-Consistent 3D Vector Graphics Synthesis