LiVER conditions video diffusion models on renderer-derived 3D control signals for disentangled, editable control over object layout, lighting, and camera trajectory.
DL3DV-10K: A large-scale scene dataset for deep learning-based 3D vision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lighting-grounded Video Generation with Renderer-based Agent Reasoning
LiVER conditions video diffusion models on renderer-derived 3D control signals for disentangled, editable control over object layout, lighting, and camera trajectory.