VTBench is a multi-dimensional benchmark with novel unpaired metrics and human preference data for evaluating image-based virtual try-on models, though the human-alignment evidence is incomplete.
Do not mask what you do not need to mask: a parser-free virtual try-on
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Models
VTBench is a multi-dimensional benchmark with novel unpaired metrics and human preference data for evaluating image-based virtual try-on models, though the human-alignment evidence is incomplete.