iDiff is a dual-branch framework with an Answer Model for robust pairwise preference prediction via view decomposition and ensembles, and a Thinking Model for structured rationale generation using templates and answer-aware supervision, winning first place in the NTIRE 2026 RAIM challenge.
To- wards open-ended visual quality comparison
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
-
iDiff: Interpretable Difference-aware Framework for Pairwise Image Quality Assessment
iDiff is a dual-branch framework with an Answer Model for robust pairwise preference prediction via view decomposition and ensembles, and a Thinking Model for structured rationale generation using templates and answer-aware supervision, winning first place in the NTIRE 2026 RAIM challenge.