VERTIGO post-trains camera trajectory generators with visual preference signals from Unity-rendered previews scored by a cinematically fine-tuned VLM, cutting character off-screen rates from 38% to near zero while improving framing and prompt adherence.
Cinemaster: A 3d-aware and controllable framework for cinematic text-to-video generation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 3years
2026 3roles
background 2polarities
background 2representative citing papers
A new occlusion-aware control module generates high-fidelity egocentric videos from sparse 3D hand joints, supported by a million-clip dataset and cross-embodiment benchmark.
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
citing papers explorer
-
VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation
VERTIGO post-trains camera trajectory generators with visual preference signals from Unity-rendered previews scored by a cinematically fine-tuned VLM, cutting character off-screen rates from 38% to near zero while improving framing and prompt adherence.
-
Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints
A new occlusion-aware control module generates high-fidelity egocentric videos from sparse 3D hand joints, supported by a million-clip dataset and cross-embodiment benchmark.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.