Related papers: DIME-Net: Neural Network-Based Dynamic Intrinsic P…

Mobile captured images can be aligned using their gyroscope sensors. Optical image stabilizer (OIS) terminates this possibility by adjusting the images during the capturing. In this work, we propose a deep network that compensates the…

Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality. While direct regression of images to object poses has limited accuracy, matching rendered images…

Image degradation caused by complex lighting conditions such as low-light and backlit scenarios is commonly encountered in real-world environments, significantly affecting image quality and downstream vision tasks. Most existing methods…

6-DoF object pose estimation from a monocular image is challenging, and a post-refinement procedure is generally needed for high-precision estimation. In this paper, we propose a framework based on a recurrent neural network (RNN) for…

Recently, tremendous human-designed and automatically searched neural networks have been applied to image denoising. However, previous works intend to handle all noisy images in a pre-defined static network architecture, which inevitably…

We present a novel method to fuse the power of deep networks with the computational efficiency of geometric and probabilistic localization algorithms. In contrast to other methods that completely replace a classical visual estimator with a…

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…

Rolling shutter distortion is highly undesirable for photography and computer vision algorithms (e.g., visual SLAM) because pixels can be potentially captured at different times and poses. In this paper, we propose a deep neural network to…

Existing Object Pose Estimation (OPE) methods for stacked scenarios are not robust to changes in object scale. This paper proposes a new 6DoF OPE network (NormNet) for different scale objects in stacked scenarios. Specifically, each…

Estimating the 6D pose of objects is beneficial for robotics tasks such as transportation, autonomous navigation, manipulation as well as in scenarios beyond robotics like virtual and augmented reality. With respect to single image pose…

This paper proposes a robust localization system that employs deep learning for better scene representation, and enhances the accuracy of 6-DOF camera pose estimation. Inspired by the fact that global scene structure can be revealed by wide…

We present a self-supervised deep pose correction (DPC) network that applies pose corrections to a visual odometry estimator to improve its accuracy. Instead of regressing inter-frame pose changes directly, we build on prior work that uses…

We introduce Diff-DOPE, a 6-DoF pose refiner that takes as input an image, a 3D textured model of an object, and an initial pose of the object. The method uses differentiable rendering to update the object pose to minimize the visual error…

Modern deep learning techniques that regress the relative camera pose between two images have difficulty dealing with challenging scenarios, such as large camera motions resulting in occlusions and significant changes in perspective that…

Deep neural networks are vulnerable to adversarial attacks. The literature is rich with algorithms that can easily craft successful adversarial examples. In contrast, the performance of defense techniques still lags behind. This paper…

We present RePOSE, a fast iterative refinement method for 6D object pose estimation. Prior methods perform refinement by feeding zoomed-in input and rendered RGB images into a CNN and directly regressing an update of a refined pose. Their…

Vision-based pose estimation plays a crucial role in the autonomous navigation of flight platforms. However, the field of view and spatial resolution of the camera limit pose estimation accuracy. This paper designs a divergent…

Perspective distortion (PD) causes unprecedented changes in shape, size, orientation, angles, and other spatial relationships of visual concepts in images. Precisely estimating camera intrinsic and extrinsic parameters is a challenging task…

Deep image prior (DIP), which utilizes a deep convolutional network (ConvNet) structure itself as an image prior, has attracted attentions in computer vision and machine learning communities. It empirically shows the effectiveness of…

This paper presents a new deep-learning based method to simultaneously calibrate the intrinsic parameters of fisheye lens and rectify the distorted images. Assuming that the distorted lines generated by fisheye projection should be straight…