Low-light scenes are prevalent in real-world applications (eg autonomous driving and
surveillance at night). Recently multi-object tracking in various practical use cases have …

Unprocessed RAW video has shown distinct advantages over sRGB video in video editing
and computer vision tasks. However capturing RAW video is challenging due to limitations …

The design of deep network architectures and training methods in computer vision has been
well-explored. However in almost all cases the images have been used as provided with …

Synthesizing the high dynamic range (HDR) image from multi-exposure images has been
extensively studied by exploiting convolutional neural networks (CNNs) recently. Despite the …

sRGB images are now the predominant choice for pre-training visual models in computer
vision research, owing to their ease of acquisition and efficient storage. Meanwhile, the …

With the popularity of snapshot mosaic hyperspectral cameras, researchers have shown
great interest in hyperspectral video processing in recent years, particularly hyperspectral …

There are specific, physics-based rules that govern the interaction of light and matter.
Though studied extensively in the greater computer vision community, these rules are …

While RAW images are efficient for image editing and perception tasks, their large size can
strain camera storage and bandwidth. Techniques exist to reconstruct RAW images from …