visual fidelity
The accuracy and realism of generated images or visual outputs in relation to their expected representation or the original content.
- 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction
- ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation
- Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
- BitMark: Watermarking Bitwise Autoregressive Image Generative Models
- Bézier Splatting for Fast and Differentiable Vector Graphics Rendering
- Denoising Trajectory Biases for Zero-Shot AI-Generated Image Detection
- EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling
- EverybodyDance: Bipartite Graph–Based Identity Correspondence for Multi-Character Animation
- LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering
- MagCache: Fast Video Generation with Magnitude-Aware Cache
- Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction
- Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection
- Rare Text Semantics Were Always There in Your Diffusion Transformer
- ReSim: Reliable World Simulation for Autonomous Driving
- Rendering-Aware Reinforcement Learning for Vector Graphics Generation
- RoboScape: Physics-informed Embodied World Model
- SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
- UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset
- UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting
- VideoTitans: Scalable Video Prediction with Integrated Short- and Long-term Memory
- X-Field: A Physically Informed Representation for 3D X-ray Reconstruction