3 papers
cs.CV2026
PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception
Kaichen Zhou, Yuhan Wang, Grace Chen +5
Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since the…
cs.CV2026
Delta Rectified Flow Sampling for Text-to-Image Editing
Gaspard Beaudouin, Minghan Li, Jaeyeon Kim +2
We propose Delta Rectified Flow Sampling (DRFS), a novel inversion-free, path-aware editing framework within rectified flow models for text-to-image editing. DRFS is a distillation…
cs.CV2025
SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing
Sung-Hoon Yoon, Minghan Li, Gaspard Beaudouin +3
Rectified flow models have become a de facto standard in image generation due to their stable sampling trajectories and high-fidelity outputs. Despite their strong generative capab…