13 papers
Label-Free Target-Domain Adaptation for Unconstrained Event-Image Feature Matching via Dual-Stage Distillation
Zhonghua Yi, Hao Shi, Qi Jiang +3
Building pixel-level correspondence between event and image data is a fundamental task for multi-sensor systems. However, existing cross-modal matching methods are largely restrict…
Towards Blind Lens Aberration Correction via Large LensLib Pre-training and Discrete Degradation Priors
Xiaolong Qian, Qi Jiang, Yao Gao +8
Emerging deep-learning-based lens library pre-training (LensLib-PT) pipeline offers a new avenue for blind lens aberration correction by training a universal neural network, demons…
Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis
Xiaolong Qian, Qi Jiang, Yao Gao +5
Prevalent Computational Aberration Correction (CAC) methods are typically tailored to specific optical systems, leading to poor generalization and labor-intensive re-training for n…
Learning Latent Transmission and Glare Maps for Lens Veiling Glare Removal
Xiaolong Qian, Qi Jiang, Lei Sun +8
Beyond the commonly recognized optical aberrations, the imaging performance of simplified optical systems--including single-lens and metalens designs--is often further degraded by…
OmniLens: Towards Universal Lens Aberration Correction via LensLib-to-Specific Domain Adaptation
Qi Jiang, Yao Gao, Shaohua Gao +7
Emerging universal Computational Aberration Correction (CAC) paradigms provide an inspiring solution to light-weight and high-quality imaging with a universal model trained on a le…
Towards Real-world Lens Active Alignment with Unlabeled Data via Domain Adaptation
Wenyong Li, Qi Jiang, Weijian Hu +5
Active Alignment (AA) is a key technology for the large-scale automated assembly of high-precision optical systems. Compared with labor-intensive per-model on-device calibration, a…