Rolling shutter and motion blur removal for depth cameras

Tourani, Siddharth; Mittal, Sudhanshu; Nagariya, Akhil; Chari, Visesh; Krishna, M. Ghanashyam

doi:10.1109/icra.2016.7487715

Cited by 10 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sterzentsenko et al [ 16 ] used self-supervision to train a deep autoencoder to combat the lack of real world datasets with noise-free ground truth depths. The work from Tourani et al [ 18 ] deals with the removal of motion artifacts from rolling shutters, which are common in structured sensors such as the Kinect. Li et al [ 19 ] use a two-branched CNN to simultaneously remove motion blur from a color and a depth image.…”

Section: Related Workmentioning

confidence: 99%

“…This fails to incorporate the inherent geometric structure of depth maps. While research on depth-only enhancement exists [ 10 , 11 ], a majority of recent work has focused on some form of intensity or RGB-guided depth enhancement, e.g., for super resolution [ 12 , 13 , 14 , 15 ], denoising [ 16 , 17 ] or motion blur removal [ 18 , 19 ]. While this greatly improves the quality of the resultant depth images, these additional RGB sensors are not always available.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Generic Framework for Depth Reconstruction Enhancement

Sommerhoff

Kolb

2022

J. Imaging

View full text Add to dashboard Cite

We propose a generic depth-refinement scheme based on GeoNet, a recent deep-learning approach for predicting depth and normals from a single color image, and extend it to be applied to any depth reconstruction task such as super resolution, denoising and deblurring, as long as the task includes a depth output. Our approach utilizes a tight coupling of the inherent geometric relationship between depth and normal maps to guide a neural network. In contrast to GeoNet, we do not utilize the original input information to the backbone reconstruction task, which leads to a generic application of our network structure. Our approach first learns a high-quality normal map from the depth image generated by the backbone method and then uses this normal map to refine the initial depth image jointly with the learned normal map. This is motivated by the fact that it is hard for neural networks to learn direct mapping between depth and normal maps without explicit geometric constraints. We show the efficiency of our method on the exemplary inverse depth-image reconstruction tasks of denoising, super resolution and removal of motion blur.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Generic Framework for Depth Reconstruction Enhancement

Sommerhoff

Kolb

2022

J. Imaging

View full text Add to dashboard Cite

show abstract

“…Few works consider the challenging situation that joint RS distortion and blur appear in the images simultane-ously. Tourani et al [36] use feature matches between depth maps to timestamp parametric ego-motion to further achieve RSCD. Their method needs multiple RGBD images as inputs.…”

Section: Joint Correction and Deblurringmentioning

confidence: 99%

Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes

Zhong¹,

Zheng²,

Sato³

2021

Preprint

View full text Add to dashboard Cite

Figure 1: Joint rolling shutter correction and deblurring (RSCD). Image degradation caused by joint rolling shutter distortion and motion blur becomes extremely complex, when both ego-motion and object-motion are involved in dynamic scenes. Existing methods for RSCD such as Mohan et al. [22] are developed for static scenes. We present the first realistic benchmark dataset (BS-RSCD) and model (JCD) to advance learning-based approaches in this field.

show abstract

“…As many computer vision algorithms such as semantic segmentation, object detection, or visual odometry rely on visual input, blurry images challenge the performance of these algorithms. It is well known that many algorithms (e.g., depth prediction, feature detection, motion estimation, or object recognition) suffer from motion blur [17], [25], [26], [33]. The motion deblurring problem has thus received considerable attention in the past [7], [17], [21], [28], [32].…”

Section: Introductionmentioning

confidence: 99%

Self-Supervised Linear Motion Deblurring

Liu

Janai

Pollefeys

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Motion blurry images challenge many computer vision algorithms, e.g., feature detection, motion estimation, or object recognition. Deep convolutional neural networks are stateof-the-art for image deblurring. However, obtaining training data with corresponding sharp and blurry image pairs can be difficult. In this paper, we present a differentiable reblur model for selfsupervised motion deblurring, which enables the network to learn from real-world blurry image sequences without relying on sharp images for supervision. Our key insight is that motion cues obtained from consecutive images yield sufficient information to inform the deblurring task. We therefore formulate deblurring as an inverse rendering problem, taking into account the physical image formation process: we first predict two deblurred images from which we estimate the corresponding optical flow. Using these predictions, we re-render the blurred images and minimize the difference with respect to the original blurry inputs. We use both synthetic and real dataset for experimental evaluations. Our experiments demonstrate that self-supervised single image deblurring is really feasible and leads to visually compelling results. Both the code and datasets are available at https://github.com/ethliup/SelfDeblur.

show abstract

Rolling shutter and motion blur removal for depth cameras

Cited by 10 publications

References 15 publications

A Generic Framework for Depth Reconstruction Enhancement

A Generic Framework for Depth Reconstruction Enhancement

Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes

Self-Supervised Linear Motion Deblurring

Contact Info

Product

Resources

About