Search papers, labs, and topics across Lattice.
This paper introduces SSMB, a novel self-supervised keypoint detector designed specifically for motion-blurred images, overcoming the limitations of traditional deblur-then-detect methods and handcrafted detectors. The approach employs a Local Discriminability Enhancement (LDE) module to improve local feature detection without requiring external pseudo-labels, utilizing a two-stage training process that includes geometric pretraining and blur-aware training. Extensive evaluations show that SSMB achieves state-of-the-art performance in keypoint detection and related tasks, significantly surpassing both supervised and self-supervised benchmarks.
SSMB sets a new standard in keypoint detection under motion blur, achieving superior performance without relying on deblurring or handcrafted features.
Keypoint detection under motion blur remains a significant challenge, as blur distorts local image structure and degrades the repeatability of feature localization. Existing approaches either rely on computationally expensive deblur-then-detect pipelines that may introduce restoration artifacts, or learn to regress the image positions of handcrafted keypoints extracted on sharp images, which reflects the assumptions of the handcrafted detector rather than what is truly repeatable under blur. We present SSMB, a deblur-free, self-supervised keypoint detector for motion-blurred images that requires neither handcrafted detectors nor external pseudo-labels. SSMB introduces the Local Discriminability Enhancement (LDE) module, which restores fine-grained local discriminability after global feature mixing. Training is performed in two stages. First, geometric pretraining on synthetic shapes bootstraps spatially discriminative keypoint detection without any external detector, just from the rendered geometry. Second, blur-aware training on real sharp-blur image pairs learns blur-invariant detection through a multi-component self-supervised objective that enforces cross-domain consistency, geometric alignment, and spatial coverage. Extensive evaluations on keypoint detection, image matching, relative pose estimation, and visual localization under motion blur demonstrate that SSMB establishes a new state-of-the-art among sparse keypoint detectors, consistently outperforming both supervised and self-supervised baselines across all tasks. Code, models, and datasets will be publicly available upon paper acceptance.
