3AM: Segment Anything with Geometric Consistency in Videos Paper • 2601.08831 • Published 1 day ago • 24
Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models Paper • 2512.21337 • Published 21 days ago • 30
LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal Paper • 2510.15868 • Published Oct 17, 2025 • 26
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery Paper • 2510.15869 • Published Oct 17, 2025 • 48
Generative Refocusing: Flexible Defocus Control from a Single Image Paper • 2512.16923 • Published 27 days ago • 38