Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence
Haesol Park,Kyoung Mu Lee +1 more
- pp 4623-4631
Reads0
Chats0
TLDR
This paper proposes a pioneering unified framework that solves four problems simultaneously, namely, dense depth reconstruction, camera pose estimation, super-resolution, and deblurring, by reflecting a physical imaging process and solving the cost minimization problem using an alternating optimization technique.Abstract:
The conventional methods for estimating camera poses and scene structures from severely blurry or low resolution images often result in failure. The off-the-shelf deblurring or super-resolution methods may show visually pleasing results. However, applying each technique independently before matching is generally unprofitable because this naive series of procedures ignores the consistency between images. In this paper, we propose a pioneering unified framework that solves four problems simultaneously, namely, dense depth reconstruction, camera pose estimation, super-resolution, and deblurring. By reflecting a physical imaging process, we formulate a cost minimization problem and solve it using an alternating optimization technique. The experimental results on both synthetic and real videos show high-quality depth maps derived from severely degraded images that contrast the failures of naive multi-view stereo methods. Our proposed method also produces outstanding deblurred and super-resolved images unlike the independent application or combination of conventional video deblurring, super-resolution methods.read more
Citations
More filters
Proceedings ArticleDOI
Learning Event-Based Motion Deblurring
TL;DR: In this article, a convolutional recurrent neural network (RNN) was proposed to integrate visual and temporal knowledge of both global and local scales in principled manner for deblurring.
Proceedings ArticleDOI
Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More
TL;DR: An innovative training strategy is proposed that learns the parameters of the student intertwined with the teachers, achieved by ``projecting'' its amalgamated features onto each teacher's domain and computing the loss.
Journal ArticleDOI
Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement
Yibing Song,Jiawei Zhang,Lijun Gong,Shengfeng He,Linchao Bao,Jinshan Pan,Qingxiong Yang,Ming-Hsuan Yang +7 more
TL;DR: This paper proposes a facial component guided deep Convolutional Neural Network to restore a coarse face image, which is denoted as the base image where the facial component is automatically generated from the input face image.
Posted Content
Learning Event-Based Motion Deblurring
TL;DR: This paper starts from a sequential formulation of event-based motion deblurring, then shows how its optimization can be unfolded with a novel end-toend deep architecture, and proposes a differentiable directional event filtering module to effectively extract rich boundary prior from the evolution of events.
Journal ArticleDOI
Gated Fusion Network for Degraded Image Super Resolution
TL;DR: A dual-branch convolutional neural network to extract base features and recovered features separately and decompose the feature extraction step into two task-independent streams can facilitate the training process by avoiding learning the mixed degradation all-in-one and thus enhance the final high-resolution prediction results.
References
More filters
Proceedings ArticleDOI
Flexible camera calibration by viewing a plane from unknown orientations
TL;DR: Compared with classical techniques which use expensive equipment, such as two or three orthogonal planes, the proposed technique is easy to use and flexible, and advances 3D computer vision one step from laboratory environments to real-world use.
Journal ArticleDOI
Fast and robust multiframe super resolution
TL;DR: This paper proposes an alternate approach using L/sub 1/ norm minimization and robust regularization based on a bilateral prior to deal with different data and noise models and demonstrates its superiority to other super-resolution methods.
Journal ArticleDOI
Direct Sparse Odometry
TL;DR: Direct Sparse Odometry (DSO) as mentioned in this paper combines a fully direct probabilistic model with consistent, joint optimization of all model parameters, including geometry represented as inverse depth in a reference frame and camera motion.
Proceedings ArticleDOI
High-accuracy stereo depth maps using structured light
TL;DR: A method for acquiring high-complexity stereo image pairs with pixel-accurate correspondence information using structured light that does not require the calibration of the light sources and yields registered disparity maps between all pairs of cameras and illumination projectors.
Proceedings ArticleDOI
Secrets of optical flow estimation and their principles
TL;DR: It is discovered that “classical” flow formulations perform surprisingly well when combined with modern optimization and implementation techniques, and while median filtering of intermediate flow fields during optimization is a key to recent performance gains, it leads to higher energy solutions.