AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Abstract Neural Radiance Fields (NeRF) is a technique for high quality novel view synthesis
from a collection of posed input images. Like most view synthesis methods, NeRF uses …

Modern handheld devices can acquire burst image sequence in a quick succession.
However, the individual acquired frames suffer from multiple degradations and are …

Optical metasurfaces, planar artificial media capable of controlling light propagation, are
transitioning from laboratory curiosity to commercial applications. This shift requires …

The photographic record is increasingly becoming an important biodiversity resource for
primary research and conservation monitoring. However, globally, there are important gaps …

Each photo in an image burst can be considered a sample of a complex 3D scene: the
product of parallax diffuse and specular materials scene motion and illuminant variation …

Cameras capture sensor RAW images and transform them into pleasant RGB images,
suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous …

Non-uniform image deblurring is a challenging task due to the lack of temporal and textural
information in the blurry image itself. Complementary information from auxiliary sensors …

In smartphones and compact cameras, the Image Signal Processor (ISP) transforms the
RAW sensor image into a human-readable sRGB image. Most popular super-resolution …

The standard Neural Radiance Fields (NeRF) paradigm employs a viewer-centered
methodology, entangling the aspects of illumination and material reflectance into emission …