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 …

Underwater perception and 3D surface reconstruction are challenging problems with broad
applications in construction, security, marine archaeology, and environmental monitoring …

We show how to turn a noisy and fragile active triangulation technique--three-pattern
structured light with a grayscale camera--into a fast and powerful tool for 3D capture: able to …

Challenging to capture, and challenging to display on a cellphone screen, the panorama
paradoxically remains both a staple and underused feature of modern mobile camera …

Abstract Recently large Vision Language (VL) models ie CLIP have demonstrated
impressive capabilities in training solely on internet-scale image-language pairs. Moreover …

The accurate reconstruction of per-pixel depth for an image is vital for many tasks in
computer graphics, computer vision, and robotics. In this paper, we present a novel …

The exponential progress in generative AI poses serious implications for the credibility of all
real images and videos. There will exist a point in the future where 1) digital content …

This paper introduces a novel approach to the fine alignment of images in a burst captured
by a handheld camera. In contrast to traditional techniques that estimate two-dimensional …

In the spaces between data-hungry generative models and measurement-rich
computational imaging, we can find the field of computational photography. Can cell phone …

Data Acquisition To acquire paired obstructed and unobstructed captures, we construct two
tripod-mounted rigs as illustrated in Fig. 1 (ab). We begin by capturing a still of the scene …