DeepDetect: Learning All-in-One Dense Keypoints
By: Shaharyar Ahmed Khan Tareen, Filza Khan Tareen
Potential Business Impact:
Finds important spots in pictures better.
Keypoint detection is the foundation of many computer vision tasks, including image registration, structure-from motion, 3D reconstruction, visual odometry, and SLAM. Traditional detectors (SIFT, SURF, ORB, BRISK, etc.) and learning based methods (SuperPoint, R2D2, LF-Net, D2-Net, etc.) have shown strong performance yet suffer from key limitations: sensitivity to photometric changes, low keypoint density and repeatability, limited adaptability to challenging scenes, and lack of semantic understanding, often failing to prioritize visually important regions. We present DeepDetect, an intelligent, all-in-one, dense keypoint detector that unifies the strengths of classical detectors using deep learning. Firstly, we create ground-truth masks by fusing outputs of 7 keypoint and 2 edge detectors, extracting diverse visual cues from corners and blobs to prominent edges and textures in the images. Afterwards, a lightweight and efficient model: ESPNet, is trained using these masks as labels, enabling DeepDetect to focus semantically on images while producing highly dense keypoints, that are adaptable to diverse and visually degraded conditions. Evaluations on the Oxford Affine Covariant Regions dataset demonstrate that DeepDetect surpasses other detectors in keypoint density, repeatability, and the number of correct matches, achieving maximum values of 0.5143 (average keypoint density), 0.9582 (average repeatability), and 59,003 (correct matches).
Similar Papers
DeepDetect: Learning All-in-One Dense Keypoints
CV and Pattern Recognition
Finds important spots in pictures better than before.
EdgePoint2: Compact Descriptors for Superior Efficiency and Accuracy
CV and Pattern Recognition
Helps robots see and understand places faster.
KeyPointDiffuser: Unsupervised 3D Keypoint Learning via Latent Diffusion Models
CV and Pattern Recognition
Teaches computers to see and build 3D shapes.