Related papers: Rolling Shutter Correction with Intermediate Disto…
Optical flow is a crucial component of the feature space for early visual processing of dynamic scenes especially in new applications such as self-driving vehicles, drones and autonomous robots. The dynamic vision sensors are well suited…
Super-resolution is an ill-posed problem, since it allows for multiple predictions for a given low-resolution image. This fundamental fact is largely ignored by state-of-the-art deep learning based approaches. These methods instead train a…
A super-resolution (SR) method for the reconstruction of Navier-Stokes (NS) flows from noisy observations is presented. In the SR method, first the observation data is averaged over a coarse grid to reduce the noise at the expense of losing…
A simple method for synchronization of video streams with a precision better than one millisecond is proposed. The method is applicable to any number of rolling shutter cameras and when a few photographic flashes or other abrupt lighting…
We propose GGS, a Generalizable Gaussian Splatting method for Autonomous Driving which can achieve realistic rendering under large viewpoint changes. Previous generalizable 3D gaussian splatting methods are limited to rendering novel views…
Teaching robots to fold, drape, or reposition deformable objects such as cloth will unlock a variety of automation applications. While remarkable progress has been made for rigid object manipulation, manipulating deformable objects poses…
Rectified Flow (RF) models achieve state-of-the-art generation quality, yet controlling them for precise tasks -- such as semantic editing or blind image recovery -- remains a challenge. Current approaches bifurcate into inversion-based…
Videos for outdoor scene often show unpleasant blur effects due to the large relative motion between the camera and the dynamic objects and large depth variations. Existing works typically focus monocular video deblurring. In this paper, we…
3D Gaussian Splatting (3DGS) has emerged as a pivotal technique for 3D scene representation, providing rapid rendering speeds and high fidelity. As 3DGS gains prominence, safeguarding its intellectual property becomes increasingly crucial…
We present a self-supervised approach to estimate flow in camera image and top-view grid map sequences using fully convolutional neural networks in the domain of automated driving. We extend existing approaches for self-supervised optical…
Optical flow is a fundamental technique for motion estimation, widely applied in video stabilization, interpolation, and object tracking. Traditional optical flow estimation methods rely on restrictive assumptions like brightness constancy…
As the original velocity field obtained from four-dimensional (4D) flow magnetic resonance imaging (MRI) contains considerable amount of noises and errors, the available Divergence-free smoothing (DFS) method can be used to process the 4D…
Achieving sharp 3D reconstruction from motion-blurred images alone becomes challenging, motivating recent methods to incorporate event cameras, benefiting from microsecond temporal resolution. However, they suffer from residual artifacts…
Distortion rectification is often required for fisheye images. The generation-based method is one mainstream solution due to its label-free property, but its naive skip-connection and overburdened decoder will cause blur and incomplete…
Most distortion correction methods focus on simple forms of distortion, such as radial or linear distortions. These works undistort images either based on measurements in the presence of a calibration grid, or use multiple views to find…
Reconstructing high-fidelity underwater scenes remains a challenging task due to light absorption, scattering, and limited visibility inherent in aquatic environments. This paper presents an enhanced Gaussian Splatting-based framework that…
Compressive video capture encodes a short high-speed video into a single measurement using a low-speed sensor, then computationally reconstructs the original video. Prior implementations rely on expensive hardware and are restricted to…
Scene flow estimation is an essential ingredient for a variety of real-world applications, especially for autonomous agents, such as self-driving cars and robots. While recent scene flow estimation approaches achieve a reasonable accuracy,…
Rectified-flow-based diffusion transformers like FLUX and OpenSora have demonstrated outstanding performance in the field of image and video generation. Despite their robust generative capabilities, these models often struggle with…
We propose a robust and fast bundle adjustment solution that estimates the 6-DoF pose of the camera and the geometry of the environment based on measurements from a rolling shutter (RS) camera. This tackles the challenges in the existing…