DispBench measures four stereo disparity models under 15 common corruptions and 5 adversarial attacks, finding transformer-based models more fragile on weather corruptions and no reliable transfer from synthetic to real corruption benchmarks.
CosPGD: an efficient white-box adversarial attack for pixel- wise prediction tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions
DispBench measures four stereo disparity models under 15 common corruptions and 5 adversarial attacks, finding transformer-based models more fragile on weather corruptions and no reliable transfer from synthetic to real corruption benchmarks.