TAR uses frozen text encoders on remote sensing scene descriptions to boost high-level features for coarse-to-fine optical-SAR image registration under large deformations.
Distinctive image features from scale-invariant keypoints
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
GESS introduces joint semantic-normal and depth stability prediction heads, the SDAK keypoint mechanism, and the UTCF descriptor fusion module to leverage multi-cue synergy for improved robustness and discriminability.
DeepDetect trains ESPNet on fused classical detector masks to produce dense, repeatable keypoints that outperform prior methods on Oxford, HPatches, and Middlebury benchmarks.
citing papers explorer
-
TAR: Text Semantic Assisted Cross-modal Image Registration Framework for Optical and SAR Images
TAR uses frozen text encoders on remote sensing scene descriptions to boost high-level features for coarse-to-fine optical-SAR image registration under large deformations.
-
GESS: Multi-cue Guided Local Feature Learning via Geometric and Semantic Synergy
GESS introduces joint semantic-normal and depth stability prediction heads, the SDAK keypoint mechanism, and the UTCF descriptor fusion module to leverage multi-cue synergy for improved robustness and discriminability.
-
DeepDetect: Learning All-in-One Dense Keypoints
DeepDetect trains ESPNet on fused classical detector masks to produce dense, repeatable keypoints that outperform prior methods on Oxford, HPatches, and Middlebury benchmarks.