Lighting-grounded Video Generation with Renderer-based Agent Reasoning

arXiv 2026 27.8 method, benchmark

TLDR

LiVER is a diffusion-based framework for scene-controllable video generation using explicit 3D properties, dense annotations, and an agent for user instructions, achieving disentangled control.

Reasoning

The paper introduces a clear framework and dataset for controllable video generation, with strong claims of state-of-the-art photorealism and consistency. However, the abstract provides limited detail on baselines, quantitative results, and limitations, making it hard to fully assess the contributions.

Read-first score

Read-first score 27.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 0.

Recency 8%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=dataset,experiment

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=dataset

Topical relevance 42%

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 432.

Keyword Scores

world model

world simulator

generative world model

interactive world model

video world model

world dynamics prediction

model-based reinforcement learning world model

Resources

Paper