RoMa sets new state-of-the-art dense feature matching performance by fusing DINOv2 features with local ConvNet features, using anchor-probability transformer decoding, and regression-by-classification loss, with a 36% gain on WxBS.
Proper reuse of image classification features im- proves object detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RoMa: Robust Dense Feature Matching
RoMa sets new state-of-the-art dense feature matching performance by fusing DINOv2 features with local ConvNet features, using anchor-probability transformer decoding, and regression-by-classification loss, with a 36% gain on WxBS.