Related papers: Digital Gimbal: End-to-end Deep Image Stabilizatio…
Computationally removing the motion blur introduced by camera shake or object motion in a captured image remains a challenging task in computational photography. Deblurring methods are often limited by the fixed global exposure time of the…
Image deblurring is an economic way to reduce certain degradations (blur and noise) in acquired images. Thus, it has become essential tool in high resolution imaging in many applications, e.g., astronomy, microscopy or computational…
Scene inference under low-light is a challenging problem due to severe noise in the captured images. One way to reduce noise is to use longer exposure during the capture. However, in the presence of motion (scene or camera motion), longer…
Unmanned aerospace vehicles usually carry sensors (i.e., electro-optical and/or infrared imaging cameras) as their primary payload. These sensors are used for image processing, target tracking, surveillance, mapping, and providing…
Real-time dense scene reconstruction during unstable camera motions is crucial for robotics, yet current RGB-D SLAM systems fail when cameras experience large viewpoint changes, fast motions, or sudden shaking. Classical optimization-based…
Capturing images under extremely low-light conditions poses significant challenges for the standard camera pipeline. Images become too dark and too noisy, which makes traditional enhancement techniques almost impossible to apply. Recently,…
Video stabilization is a fundamental and important technique for higher quality videos. Prior works have extensively explored video stabilization, but most of them involve cropping of the frame boundaries and introduce moderate levels of…
Vision-based perception systems are typically exposed to large orientation changes in different robot applications. In such conditions, their performance might be compromised due to the inherent complexity of processing data captured under…
Photosequencing aims to transform a motion blurred image to a sequence of sharp images. This problem is challenging due to the inherent ambiguities in temporal ordering as well as the recovery of lost spatial textures due to blur. Adopting…
Capturing images under extremely low-light conditions poses significant challenges for the standard camera pipeline. Images become too dark and too noisy, which makes traditional image enhancement techniques almost impossible to apply. Very…
Video stabilization algorithms are of greater importance nowadays with the prevalence of hand-held devices which unavoidably produce videos with undesirable shaky motions. In this paper we propose a data-driven online video stabilization…
We introduce a novel technique to mitigate the adverse effects of atmospheric turbulence on astronomical imaging. Utilizing a video-to-image neural network trained on simulated data, our method processes a sliding sequence of short-exposure…
Visual SLAM algorithms have been enhanced through the exploration of Gaussian Splatting representations, particularly in generating high-fidelity dense maps. While existing methods perform reliably in static environments, they often…
Non-uniform blind deblurring for general dynamic scenes is a challenging computer vision problem as blurs arise not only from multiple object motions but also from camera shake, scene depth variation. To remove these complicated motion…
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 such event sensors are being explored to address these…
Existing video stabilization methods often generate visible distortion or require aggressive cropping of frame boundaries, resulting in smaller field of views. In this work, we present a frame synthesis algorithm to achieve full-frame video…
Recent work has shown impressive results on data-driven defocus deblurring using the two-image views available on modern dual-pixel (DP) sensors. One significant challenge in this line of research is access to DP data. Despite many cameras…
We present a technique for synthesizing a motion blurred image from a pair of unblurred images captured in succession. To build this system we motivate and design a differentiable "line prediction" layer to be used as part of a neural…
Currently, many blind deblurring methods assume blurred images are noise-free and perform unsatisfactorily on the blurry images with noise. Unfortunately, noise is quite common in real scenes. A straightforward solution is to denoise images…
Dense 3D reconstruction from RGB images traditionally assumes static camera pose estimates. This assumption has endured, even as recent works have increasingly focused on real-time methods for mobile devices. However, the assumption of a…