Compressive epsilon photography for post-capture control in digital imaging

Ito, Atsushi; Tambe, Salil; Mitra, Kaushik; Sankaranarayanan, Aswin C.; Veeraraghavan, Ashok

doi:10.1145/2601097.2601207

Cited by 11 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another type of approach for HDR imaging, following the principles of epsilon photography [36], involves taking a series of images with different exposure times with a standard camera through exposure bracketing, and then combining them into an HDR image using a hat function [24] or fusion weights based on the statistical characteristic of the sensor noise [26], [37]. The merging can also be performed using either patch-based methods [38], [39], [40], low rank matrix completion (LRMC) [41], [42], [43], [44], and more recently deep learning methods [45].…”

Section: Quantization Noise N Quan < L a T E X I T S H A 1 _ B A S E 6 4 = " E Y Z 0 2 3 N T B / S J 4 T A 1 H 0 D H E Y K N M H 0 = " >mentioning

confidence: 99%

“…The merging can also be performed using either patch-based methods [38], [39], [40], low rank matrix completion (LRMC) [41], [42], [43], [44], and more recently deep learning methods [45]. A model of per pixel intensity variations, observed when the camera parameters are varied, is proposed in [36], inspired by the confocal stereo method [46].…”

Section: Quantization Noise N Quan < L a T E X I T S H A 1 _ B A S E 6 4 = " E Y Z 0 2 3 N T B / S J 4 T A 1 H 0 D H E Y K N M H 0 = " >mentioning

confidence: 99%

See 1 more Smart Citation

Compressive HDR Light Field Imaging Using a Single Multi-ISO Sensor

Miandji¹,

Nguyen²,

Hajisharif³

et al. 2021

IEEE Trans. Comput. Imaging

View full text Add to dashboard Cite

In this paper, we propose a new design for single sensor compressive HDR light field cameras, combining multi-ISO photography with coded mask acquisition, placed in a compressive sensing framework. The proposed camera model is based on a main lens, a multi-ISO sensor and a coded mask located in the optical path between the main lens and the sensor that projects the coded spatio-angular information of the light field onto the 2D sensor. The model encompasses different acquisition scenarios with different ISO patterns and gains. Moreover, we assume that the sensor has a built-in color filter array (CFA), making our design more suitable for consumer-level cameras. We propose a reconstruction algorithm to jointly perform color demosaicing, light field angular information recovery, HDR reconstruction, and denoising from the multi-ISO measurements formed on the sensor. This is achieved by enabling the sparse representation of HDR light fields using an overcomplete HDR dictionary. We also provide two HDR light field data sets: one synthetic data set created using the Blender rendering software with two baselines, and a real light field data set created from the fusion of multi-exposure low dynamic range (LDR) images captured using a Lytro Illum light field camera. Experimental results show that, with a sampling rate as low as 2.67%, using two shots, our proposed method yields a higher light field reconstruction quality compared to the fusion of multiple LDR light fields captured with different exposures, and with the fusion of multiple LDR light fields captured with different ISO settings.

show abstract

Section: Quantization Noise N Quan < L a T E X I T S H A 1 _ B A S E 6 4 = " E Y Z 0 2 3 N T B / S J 4 T A 1 H 0 D H E Y K N M H 0 = " >mentioning

confidence: 99%

Section: Quantization Noise N Quan < L a T E X I T S H A 1 _ B A S E 6 4 = " E Y Z 0 2 3 N T B / S J 4 T A 1 H 0 D H E Y K N M H 0 = " >mentioning

confidence: 99%

Compressive HDR Light Field Imaging Using a Single Multi-ISO Sensor

Miandji¹,

Nguyen²,

Hajisharif³

et al. 2021

IEEE Trans. Comput. Imaging

View full text Add to dashboard Cite

show abstract

“…The opposite direction of enrichment in this tandem has been inexplicably underestimated by the community until very recently [4]. In particular, the embedded algorithms rarely use the arsenal of image-improving hardware components within the camera to adjust/update themselves.…”

Section: Introductionmentioning

confidence: 99%

DASHA: Decentralized Autofocusing System with Hierarchical Agents

Anikina¹,

Rogov²,

Dylov³

2021

Preprint

View full text Add to dashboard Cite

State-of-the-art object detection models are frequently trained offline using available datasets, such as ImageNet: large and overly diverse data that are unbalanced and hard to cluster semantically. This kind of training drops the object detection performance should the change in illumination, in the environmental conditions (e.g., rain), or in the lens positioning (out-of-focus blur) occur. We propose a decentralized hierarchical multi-agent deep reinforcement learning approach for intelligently controlling the camera and the lens focusing settings, leading to significant improvement to the capacity of the popular detection models (YOLO, Fast R-CNN, and Retina are considered). The algorithm relies on the latent representation of the camera's stream and, thus, it is the first method to allow a completely no-reference tuning of the camera, where the system trains itself to auto-focus itself.

show abstract

“…Nagahara et al [2] expanded the degrees-of-freedom (DOFs) by using a sweeping camera. Ito et al [3] simulated a photographic image using compressive epsilon photography. Although these methods enable us to later change the point of focus and DOFs, they require unique and expensive equipment or long processing times.…”

Section: Introductionmentioning

confidence: 99%

Focusness Extraction from Images for Automatic Camera Control by Measuring Objectness

Tanaka¹,

Kiyomitsu²,

Maki³

et al. 2018

jist

View full text Add to dashboard Cite

Current digital cameras have various automatic control systems. In automatic camera systems, extracting focusness from an image is a very important problem. Automatic extraction of the main subject makes taking photos very easy, even for an amateur photographer. Methods have been proposed to evaluate focusness by visual saliency, which assume that an area with high saliency also has high focusness. However, various differences exist between focusness and saliency. In this study, we compare the values between focusness and saliency maps. We evaluate the focusness of 80 images in an image evaluation experiment with 20 observers. Saliency maps are calculated using six conventional algorithms. We show that the individual variations of focusness are very few in images that include only one major object. Furthermore, we apply a GIST feature to the saliency method by using a center-surround histogram and extract focusness from images with high accuracy.

show abstract

Compressive epsilon photography for post-capture control in digital imaging

Cited by 11 publications

References 42 publications

Compressive HDR Light Field Imaging Using a Single Multi-ISO Sensor

Compressive HDR Light Field Imaging Using a Single Multi-ISO Sensor

DASHA: Decentralized Autofocusing System with Hierarchical Agents

Focusness Extraction from Images for Automatic Camera Control by Measuring Objectness

Contact Info

Product

Resources

About