PhyCoBench and PhyCoPredictor provide a new benchmark and a learned optical-flow-guided evaluator for physical coherence of text-to-video models, but the evaluator's agreement with humans is modest (Kendall tau 0.34).
Videocrafter2: Overcoming data limitations for high-quality video diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Physical Coherence Benchmark for Evaluating Video Generation Models via Optical Flow-guided Frame Prediction
PhyCoBench and PhyCoPredictor provide a new benchmark and a learned optical-flow-guided evaluator for physical coherence of text-to-video models, but the evaluator's agreement with humans is modest (Kendall tau 0.34).