Image Quality Is Not All You Want: Task-Driven Lens Design for Image Classification
In computer vision, it has long been taken for granted that high-quality images obtained through well-designed camera lenses would lead to superior results. However, we find that this common perception is not a "one-size-fits-all" solution for diverse computer vision tasks. We demonstrate that task-driven and deep-learned simple optics can actually deliver better visual task performance. The Task-Driven lens design approach, which relies solely on a well-trained network model for supervision, is proven to be capable of designing lenses from scratch. Experimental results demonstrate the designed image classification lens (``TaskLens'') exhibits higher accuracy compared to conventional imaging-driven lenses, even with fewer lens elements. Furthermore, we show that our TaskLens is compatible with various network models while maintaining enhanced classification accuracy. We propose that TaskLens holds significant potential, particularly when physical dimensions and cost are severely constrained.
Code (0)
등록된 구현이 없습니다.
Tasks
Allimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
A generative approach for lensless imaging in low-light conditions
Lensless imaging offers a lightweight, compact alternative to traditional lens-based systems, ideal for exploration in space-constrained environments. However, the absence of a focusing lens and limited lighting in such …
Let There Be Light: Robust Lensless Imaging Under External Illumination With Deep Learning
Lensless cameras relax the design constraints of traditional cameras by shifting image formation from analog optics to digital post-processing. While new camera designs and applications can be enabled, lensless imaging i…
Scalable dataset acquisition for data-driven lensless imaging
Data-driven developments in lensless imaging, such as machine learning-based reconstruction algorithms, require large datasets. In this work, we introduce a data acquisition pipeline that can capture from multiple lensle…
Saliency-Guided Textured Contact Lens-Aware Iris Recognition
Iris recognition requires an adequate level of the iris texture being visible to perform a reliable matching. In case when a textured contact lens covers the iris, a false non-match is reported or a presentation attack i…
Iris RecognitionIris SegmentationWide-Angle Rectification via Content-Aware Conformal Mapping
Despite the proliferation of ultra wide-angle lenses on smartphone cameras, such lenses often come with severe image distortion (e.g. curved linear structure, unnaturally skewed faces). Most existing rectification me…