2 papers
cs.CV2026
GLoD-LVSM: Learning Geometry-Grounded Continuous-LoD Scene Representations for Large View Synthesis Models
Weikai Lin, Nicholas Milef, Carl S Marshall +3
Large view synthesis models (LVSMs) reconstruct scenes from sparse views and render novel views quickly, but they incur unnecessary storage and rendering costs due to token redunda…
cs.CV2026
EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing
Yehonathan Litman, Shikun Liu, Dario Seyb +5
High-fidelity generative video editing has seen significant quality improvements by leveraging pre-trained video foundation models. However, their computational cost is a major bot…