OmniShotCut Omni Running on Zero Agents 14 OmniShotCut 🌖 14 A more informative SoTA on Shot Boundary Detection uva-cv-lab/OmniShotCut Updated 9 days ago • 6 OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer Paper • 2604.24762 • Published 11 days ago • 13
OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer Paper • 2604.24762 • Published 11 days ago • 13
WildRayZer Checkpoints and Data Release for WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments (CVPR 2026 Highlight) uva-cv-lab/wildrayzer-checkpoints Image-to-Image • Updated 21 days ago uva-cv-lab/Dynamic-RE10K Preview • Updated 28 days ago • 792 • 6 Running on Zero Agents 1 WildRayZer 🎥 1 Generate new views of a scene from a few photos
SAB3R Checkpoints and Demo release for SAB3R: Semantic-Augmented Backbone in 3D Reconstruction Running on Zero Agents 1 SAB3R 🌐 1 Generate descriptive captions for your photos uva-cv-lab/SAB3R Updated Jun 8, 2025
Frame In-N-Out The model zoo for "Unbounded Controllable Image-to-Video Generation." uva-cv-lab/FrameINO_data Updated Dec 29, 2025 • 5 • 3 uva-cv-lab/FrameINO_CogVideoX_Stage2_MotionINO_v1.0 Updated Nov 19, 2025 • 13 • 3 uva-cv-lab/FrameINO_CogVideoX_Stage1_Motion_v1.0 Updated Nov 19, 2025 • 12 • 3 uva-cv-lab/FrameINO_Wan2.2_5B_Stage2_MotionINO_v1.5 Updated Nov 19, 2025 • 6 • 3
OmniShotCut Omni Running on Zero Agents 14 OmniShotCut 🌖 14 A more informative SoTA on Shot Boundary Detection uva-cv-lab/OmniShotCut Updated 9 days ago • 6 OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer Paper • 2604.24762 • Published 11 days ago • 13
OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer Paper • 2604.24762 • Published 11 days ago • 13
SAB3R Checkpoints and Demo release for SAB3R: Semantic-Augmented Backbone in 3D Reconstruction Running on Zero Agents 1 SAB3R 🌐 1 Generate descriptive captions for your photos uva-cv-lab/SAB3R Updated Jun 8, 2025
WildRayZer Checkpoints and Data Release for WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments (CVPR 2026 Highlight) uva-cv-lab/wildrayzer-checkpoints Image-to-Image • Updated 21 days ago uva-cv-lab/Dynamic-RE10K Preview • Updated 28 days ago • 792 • 6 Running on Zero Agents 1 WildRayZer 🎥 1 Generate new views of a scene from a few photos
Frame In-N-Out The model zoo for "Unbounded Controllable Image-to-Video Generation." uva-cv-lab/FrameINO_data Updated Dec 29, 2025 • 5 • 3 uva-cv-lab/FrameINO_CogVideoX_Stage2_MotionINO_v1.0 Updated Nov 19, 2025 • 13 • 3 uva-cv-lab/FrameINO_CogVideoX_Stage1_Motion_v1.0 Updated Nov 19, 2025 • 12 • 3 uva-cv-lab/FrameINO_Wan2.2_5B_Stage2_MotionINO_v1.5 Updated Nov 19, 2025 • 6 • 3
