Search
Results
-
Deep Shutter Unrolling Network
(2020)2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)We present a novel network for rolling shutter effect correction. Our network takes two consecutive rolling shutter images and estimates the corresponding global shutter image of the latest frame. The dense displacement field from a rolling shutter image to its corresponding global shutter image is estimated via a motion estimation network. The learned feature representation of a rolling shutter image is then warped, via the displacement ...Conference Paper -
Self-Supervised Human Depth Estimation From Monocular Videos
(2020)2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Previous methods on estimating detailed human depth often require supervised training with `ground truth' depth data. This paper presents a self-supervised method that can be trained on YouTube videos without known depth, which makes training data collection simple and improves the generalization of the learned network. The self-supervised learning is achieved by minimizing a photo-consistency loss, which is evaluated between a video frame ...Conference Paper -
Calibration-Free Structure-from-Motion with Calibrated Radial Trifocal Tensors
(2020)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2020In this paper we consider the problem of Structure-from-Motion from images with unknown intrinsic calibration. Instead of estimating the internal camera parameters through some self-calibration procedure, we propose to use a subset of the reprojection constraints that is invariant to radial displacement. This allows us to recover metric 3D reconstructions without explicitly estimating the cameras’ focal length or radial distortion parameters. ...Conference Paper -
Privacy Preserving Structure-from-Motion
(2020)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2020Over the last years, visual localization and mapping solutions have been adopted by an increasing number of mixed reality and robotics systems. The recent trend towards cloud-based localization and mapping systems has raised significant privacy concerns. These are mainly grounded by the fact that these services require users to upload visual data to their servers, which can reveal potentially confidential information, even if only derived ...Conference Paper -
Infrastructure-Based Multi-camera Calibration Using Radial Projections
(2020)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2020Multi-camera systems are an important sensor platform for intelligent systems such as self-driving cars. Pattern-based calibration techniques can be used to calibrate the intrinsics of the cameras individually. However, extrinsic calibration of systems with little to no visual overlap between the cameras is a challenge. Given the camera intrinsics, infrastructure-based calibration techniques are able to estimate the extrinsics using 3D ...Conference Paper -
Convolutional Occupancy Networks
(2020)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2020Recently, implicit neural representations have gained popularity for learning-based 3D reconstruction. While demonstrating promising results, most implicit approaches are limited to comparably simple geometry of single objects and do not scale to more complicated or large-scale scenes. The key limiting factor of implicit methods is their simple fully-connected network architecture which does not allow for integrating local information in ...Conference Paper -
Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object Reconstruction
(2020)2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Modeling hand-object manipulations is essential for understanding how humans interact with their environment. While of practical importance, estimating the pose of hands and objects during interactions is challenging due to the large mutual occlusions that occur during manipulation. Recent efforts have been directed towards fully-supervised methods that require large amounts of labeled training samples. Collecting 3D ground-truth data for ...Conference Paper -
Multi-view Optimization of Local Feature Geometry
(2020)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2020In this work, we address the problem of refining the geometry of local image features from multiple views without known scene or camera geometry. Current approaches to local feature detection are inherently limited in their keypoint localization accuracy because they only operate on a single view. This limitation has a negative impact on downstream tasks such as Structure-from-Motion, where inaccurate keypoints lead to large errors in ...Conference Paper -
Handcrafted Outlier Detection Revisited
(2020)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2020Local feature matching is a critical part of many computer vision pipelines, including among others Structure-from-Motion, SLAM, and Visual Localization. However, due to limitations in the descriptors, raw matches are often contaminated by a majority of outliers. As a result, outlier detection is a fundamental problem in computer vision and a wide range of approaches, from simple checks based on descriptor similarity to geometric verification, ...Conference Paper -
Polarimetric Relative Pose Estimation
(2020)2019 IEEE/CVF International Conference on Computer Vision (ICCV)n this paper we consider the problem of relative pose estimation from two images with per-pixel polarimetric information. Using these additional measurements we derive a simple minimal solver for the essential matrix which only requires two point correspondences. The polarization constraints allow us to pointwise recover the 3D surface normal up to a two-fold ambiguity for the diffuse reflection. Since this ambiguity exists per point, ...Conference Paper