Related papers: SAMP: Shape and Motion Priors for 4D Vehicle Recon…

We present a self-supervised learning framework to estimate the individual object motion and monocular depth from video. We model the object motion as a 6 degree-of-freedom rigid-body transformation. The instance segmentation mask is…

We consider the task of estimating 3D human pose and shape from videos. While existing frame-based approaches have made significant progress, these methods are independently applied to each image, thereby often leading to inconsistent…

Depth acquisition, based on active illumination, is essential for autonomous and robotic navigation. LiDARs (Light Detection And Ranging) with mechanical, fixed, sampling templates are commonly used in today's autonomous vehicles. An…

In MRI, motion artefacts are among the most common types of artefacts. They can degrade images and render them unusable for accurate diagnosis. Traditional methods, such as prospective or retrospective motion correction, have been proposed…

Robots need both visual and contact sensing to effectively estimate the state of their environment. Camera RGBD data provides rich information of the objects surrounding the robot, and shape priors can help correct noise and fill in gaps…

The elliptical shape prior information plays a vital role in improving the accuracy of image segmentation for specific tasks in medical and natural images. Existing deep learning-based segmentation methods, including the Segment Anything…

We present a method for the accurate 3D reconstruction of partly-symmetric objects. We build on the strengths of recent advances in neural reconstruction and rendering such as Neural Radiance Fields (NeRF). A major shortcoming of such…

Joint camera pose and dense geometry estimation from a set of images or a monocular video remains a challenging problem due to its computational complexity and inherent visual ambiguities. Most dense incremental reconstruction systems…

3D object detection with point clouds and images plays an important role in perception tasks such as autonomous driving. Current methods show great performance on detection and pose estimation of standard-shaped vehicles but lack behind on…

Realistic simulation is key to enabling safe and scalable development of % self-driving vehicles. A core component is simulating the sensors so that the entire autonomy system can be tested in simulation. Sensor simulation involves modeling…

In medical imaging, point distribution models are often used to reconstruct and complete partial shapes using a statistical model of the full shape. A commonly overlooked, but crucial factor in this reconstruction process, is the pose of…

In this paper, we propose a novel method for joint recovery of camera pose, object geometry and spatially-varying Bidirectional Reflectance Distribution Function (svBRDF) of 3D scenes that exceed object-scale and hence cannot be captured…

Tracking in urban street scenes plays a central role in autonomous systems such as self-driving cars. Most of the current vision-based tracking methods perform tracking in the image domain. Other approaches, eg based on LIDAR and radar,…

An approach is proposed for high resolution 3D reconstruction of an object using a Micro Air Vehicle (MAV). A system is described which autonomously captures images and performs a dense 3D reconstruction via structure from motion with no…

Active 3D measurement, especially structured light (SL) has been widely used in various fields for its robustness against textureless or equivalent surfaces by low light illumination. In addition, reconstruction of large scenes by moving…

Reconstructing 3D vehicles from noisy and sparse partial point clouds is of great significance to autonomous driving. Most existing 3D reconstruction methods cannot be directly applied to this problem because they are elaborately designed…

Structure from Motion (SfM) is a critical task in computer vision, aiming to recover the 3D scene structure and camera motion from a sequence of 2D images. The recent pose-only imaging geometry decouples 3D coordinates from camera poses and…

Motivated by the growing demand for interactive environments, we propose an accurate real-time 3D shape reconstruction technique. To provide a reliable 3D reconstruction which is still a challenging task when dealing with real-world…

Dense 3D reconstruction has many applications in automated driving including automated annotation validation, multimodal data augmentation, providing ground truth annotations for systems lacking LiDAR, as well as enhancing auto-labeling…

Existing marker-less motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, which narrows its application scenarios. Here we propose a fully automatic method that given multi-view video,…