Multi-Shot Deblurring for 3D Scenes

Arun, M.; Rajagopalan, A. N.; Seetharaman, Gunasekaran

doi:10.1109/iccvw.2015.37

Cited by 6 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hu et al [13] solved it as a segment-wise depth estimation problem by assuming a discrete-layered scene where each segment corresponds to one layer. Arun et al [3] proposed a geometric algorithm to estimate the camera motion from the blurry images themselves. However, they all assume that the scene to be static and the camera motion is the only source of motion blur.…”

Section: Related Workmentioning

confidence: 99%

“…High-precision and high-resolution 3D information play significant role in a variety of computer vision tasks including autonomous navigation [10,19], 3D reconstruction and modeling [20,35], and image deblurring [3,13,32,37] just to count a few. However, the acquisition of such accurate depth maps is a challenging task.…”

Section: Introductionmentioning

confidence: 99%

“…Existing works use multiple-view blurry images to estimate the depth and deblur the image [3,13,32]. Even though they demonstrate that the depth estimation would also benefit image deblurring, their frameworks cannot be directly adopted to solve our problem, since they make strong assumptions that the scene is static, and the blur is only due to camera shake.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Depth Map Completion by Jointly Exploiting Blurry Color Images and Sparse Depth Maps

Pan

Dai

Liu

et al. 2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

We aim at predicting a complete and high-resolution depth map from incomplete, sparse and noisy depth measurements. Existing methods handle this problem either by exploiting various regularizations on the depth maps directly or resorting to learning based methods. When the corresponding color images are available, the correlation between the depth maps and the color images are used to improve the completion performance, assuming the color images are clean and sharp. However, in real world dynamic scenes, color images are often blurry due to the camera motion and the moving objects in the scene. In this paper, we propose to tackle the problem of depth map completion by jointly exploiting the blurry color image sequences and the sparse depth map measurements, and present an energy minimization based formulation to simultaneously complete the depth maps, estimate the scene flow and deblur the color images. Our experimental evaluations on both outdoor and indoor scenarios demonstrate the stateof-the-art performance of our approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Depth Map Completion by Jointly Exploiting Blurry Color Images and Sparse Depth Maps

Pan

Dai

Liu

et al. 2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

show abstract

“…Connecting deblurring and depth estimation, Xu and Jia [27] successfully apply stereo correspondence estimation to motion-blurred stereo frames to support blind image deblurring. Lee and Lee [28], Arun et al [29], and Hu et al [30] estimate sharp images and depth jointly. However, all these approaches assume the scene to be static and camera motion to be the only source of motion blur.…”

Section: Fig 2 Stereo Video Deblurringmentioning

confidence: 99%

Stereo Video Deblurring

Sellent

Rother

Roth

2016

Computer Vision – ECCV 2016

View full text Add to dashboard Cite

Abstract. Videos acquired in low-light conditions often exhibit motion blur, which depends on the motion of the objects relative to the camera. This is not only visually unpleasing, but can hamper further processing. With this paper we are the first to show how the availability of stereo video can aid the challenging video deblurring task. We leverage 3D scene flow, which can be estimated robustly even under adverse conditions. We go beyond simply determining the object motion in two ways: First, we show how a piecewise rigid 3D scene flow representation allows to induce accurate blur kernels via local homographies. Second, we exploit the estimated motion boundaries of the 3D scene flow to mitigate ringing artifacts using an iterative weighting scheme. Being aware of 3D object motion, our approach can deal robustly with an arbitrary number of independently moving objects. We demonstrate its benefit over state-of-the-art video deblurring using quantitative and qualitative experiments on rendered scenes and real videos.

show abstract

“…Enfin les travaux plus récents de [HUE et al, 2014] et [ARUN et al, 2015 abordent le problème sous l'angle d'une « déconvolution aveugle » où les paramètres à estimer sont les mouvements de la caméra (rotations et translations) ainsi que la profondeur de la scène photographiée. Les estimations se font par itérations.…”

Section: Travaux Antérieursunclassified

Correction du flou de mouvement sur des images prises de nuit depuis un véhicule de numérisation terrestre

Daval¹,

Lelégard²,

Brédif³

2017

RFPT

View full text Add to dashboard Cite

Ce travail marque une première étape dans la définition d'une méthode de correction du flou de mouvement observé dans les clichés pris avec un long temps d'exposition par un véhicule de cartographie mobile. Dans l'approche proposée, nous prenons en considération à la fois les données inertielles provenant d'accéléromètres et de gyroscopes et les données de variation de la profondeur de la scène fournies par des mesures Lidar ou un modèle 3D. Notre algorithme utilise toutes les données utiles afin de déterminer au mieux la fonction d'étalement du point en chaque pixel. Nous proposons également un premier essai de correction du flou en utilisant les noyaux de flou non uniforme et spatialement variant que nous avons obtenus en suivant une approche de reconstruction spatiale. Notre méthode est actuellement validée sur des prises de vue floues non bruitées obtenues par images de synthèse qui reproduisent le mouvement réel du véhicule. Nous précisons enfin comment il est envisagé d'obtenir une correction de l'image complète et d'améliorer encore ces premiers travaux.

show abstract

Multi-Shot Deblurring for 3D Scenes

Cited by 6 publications

References 23 publications

Depth Map Completion by Jointly Exploiting Blurry Color Images and Sparse Depth Maps

Depth Map Completion by Jointly Exploiting Blurry Color Images and Sparse Depth Maps

Stereo Video Deblurring

Correction du flou de mouvement sur des images prises de nuit depuis un véhicule de numérisation terrestre

Contact Info

Product

Resources

About