Similar Items: From Web to Pixels: Bringing Agentic Search into Visual Perception
- OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
- Pixal3D: Pixel-Aligned 3D Generation from Images
- Pixel Perfect: Relational Image Quality Assessment with Spatially-Aware Distortions
- FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation
- Beyond Pixel Fidelity: Minimizing Perceptual Distortion and Color Bias in Night Photography Rendering
- Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs