公开(公告)号：US09129388B2

公开(公告)日：2015-09-08

申请号：US13683020

申请日：2012-11-21

Applicant: Apple Inc.

Inventor： Graham D. Finlayson ,  Jakkarin Singnoo

IPC: G06K9/00 ,  G06T5/00

CPC classification number: G06T5/002 ,  G06T5/009 ,  G06T5/40 ,  G06T2207/10024 ,  G06T2207/20192 ,  G06T2207/20208

Abstract: Techniques to generate global tone-mapping operators (G-TMOs) that, when applied to high dynamic range images, visually approximate the use of spatially varying tone-mapping operators (SV-TMOs) are described. The disclosed G-TMOs provide substantially the same visual benefits as SV-TMOs but do not suffer from spatial artifacts such as halos and are, in addition, computationally efficient compared to SV-TMOs. In general, G-TMOs may be identified based on application of a SV-TMO to a down-sampled version of a full-resolution input image (e.g., a thumbnail). An optimized mapping between the SV-TMO's input and output constitutes the G-TMO. It has been unexpectedly discovered that when optimized (e.g., to minimize the error between the SV-TMO's input and output), G-TMOs so generated provide an excellent visual approximation to the SV-TMO (as applied to the full-resolution image).

Abstract translation: 描述了当应用于高动态范围图像时视觉上近似使用空间变化色调映射算子（SV-TMO）的生成全局色调映射算子（G-TMO）的技术。 所公开的G-TMO提供与SV-TMO基本上相同的视觉效果，但是不会像诸如光晕那样的空间伪影，而且与SV-TMO相比，计算效率更高。 通常，可以基于将SV-TMO应用于全分辨率输入图像（例如，缩略图）的下采样版本来识别G-TMO。 SV-TMO的输入和输出之间的优化映射构成了G-TMO。 已经意外地发现，当优化时（例如，为了最小化SV-TMO的输入和输出之间的误差），所生成的G-TMO提供了对SV-TMO的极好的视觉近似（应用于全分辨率图像） 。

公开(公告)号：US09626744B2

公开(公告)日：2017-04-18

申请号：US14840843

申请日：2015-08-31

Applicant: Apple Inc.

Inventor： Graham D. Finlayson ,  Jakkarin Singnoo

IPC: G06K9/00 ,  G06T5/00 ,  G06T5/40

CPC classification number: G06T5/002 ,  G06T5/009 ,  G06T5/40 ,  G06T2207/10024 ,  G06T2207/20192 ,  G06T2207/20208

Abstract: Techniques to generate global tone-mapping operators (G-TMOs) that, when applied to high dynamic range images, visually approximate the use of spatially varying tone-mapping operators (SV-TMOs) are described. The disclosed G-TMOs provide substantially the same visual benefits as SV-TMOs but do not suffer from spatial artifacts such as halos and are, in addition, computationally efficient compared to SV-TMOs. In general, G-TMOs may be identified based on application of a SV-TMO to a down-sampled version of a full-resolution input image (e.g., a thumbnail). An optimized mapping between the SV-TMO's input and output constitutes the G-TMO. It has been unexpectedly discovered that when optimized (e.g., to minimize the error between the SV-TMO's input and output), G-TMOs so generated provide an excellent visual approximation to the SV-TMO (as applied to the full-resolution image).

公开(公告)号：US09858652B2

公开(公告)日：2018-01-02

申请号：US15449523

申请日：2017-03-03

Applicant: Apple Inc.

Inventor： Graham D. Finlayson ,  Jakkarin Singnoo

IPC: G06K9/00 ,  G06T5/00 ,  G06T5/40

CPC classification number: G06T5/002 ,  G06T5/009 ,  G06T5/40 ,  G06T2207/10024 ,  G06T2207/20192 ,  G06T2207/20208

Abstract: Techniques to generate global tone-mapping operators (G-TMOs) that, when applied to high dynamic range images, visually approximate the use of spatially varying tone-mapping operators (SV-TMOs) are described. The disclosed G-TMOs provide substantially the same visual benefits as SV-TMOs but do not suffer from spatial artifacts such as halos and are, in addition, computationally efficient compared to SV-TMOs. In general, G-TMOs may be identified based on application of a SV-TMO to a down-sampled version of a full-resolution input image (e.g., a thumbnail). An optimized mapping between the SV-TMO's input and output constitutes the G-TMO. It has been unexpectedly discovered that when optimized (e.g., to minimize the error between the SV-TMO's input and output), G-TMOs so generated provide an excellent visual approximation to the SV-TMO (as applied to the full-resolution image).

公开(公告)号：US20170018059A1

公开(公告)日：2017-01-19

申请号：US14840843

申请日：2015-08-31

Applicant: Apple Inc.

Inventor： Graham D. Finlayson ,  Jakkarin Singnoo

IPC: G06T5/00 ,  G06T5/40

CPC classification number: G06T5/002 ,  G06T5/009 ,  G06T5/40 ,  G06T2207/10024 ,  G06T2207/20192 ,  G06T2207/20208

Abstract: Techniques to generate global tone-mapping operators (G-TMOs) that, when applied to high dynamic range images, visually approximate the use of spatially varying tone-mapping operators (SV-TMOs) are described. The disclosed G-TMOs provide substantially the same visual benefits as SV-TMOs but do not suffer from spatial artifacts such as halos and are, in addition, computationally efficient compared to SV-TMOs. In general, G-TMOs may be identified based on application of a SV-TMO to a down-sampled version of a full-resolution input image (e.g., a thumbnail). An optimized mapping between the SV-TMO's input and output constitutes the G-TMO. It has been unexpectedly discovered that when optimized (e.g., to minimize the error between the SV-TMO's input and output), G-TMOs so generated provide an excellent visual approximation to the SV-TMO (as applied to the full-resolution image).

Abstract translation: 描述了当应用于高动态范围图像时视觉上近似使用空间变化色调映射算子（SV-TMO）的生成全局色调映射算子（G-TMO）的技术。 所公开的G-TMO提供与SV-TMO基本上相同的视觉效果，但是不会像诸如光晕那样的空间伪影，而且与SV-TMO相比，计算效率更高。 通常，可以基于将SV-TMO应用于全分辨率输入图像（例如，缩略图）的下采样版本来识别G-TMO。 SV-TMO的输入和输出之间的优化映射构成了G-TMO。 已经意外地发现，当优化时（例如，为了最小化SV-TMO的输入和输出之间的误差），所生成的G-TMO提供了对SV-TMO的极好的视觉近似（应用于全分辨率图像） 。

公开(公告)号：US20170178302A1

公开(公告)日：2017-06-22

申请号：US15449523

申请日：2017-03-03

Applicant: Apple Inc.

Inventor： Graham D. Finlayson ,  Jakkarin Singnoo

IPC: G06T5/00

CPC classification number: G06T5/002 ,  G06T5/009 ,  G06T5/40 ,  G06T2207/10024 ,  G06T2207/20192 ,  G06T2207/20208

Abstract: Techniques to generate global tone-mapping operators (G-TMOs) that, when applied to high dynamic range images, visually approximate the use of spatially varying tone-mapping operators (SV-TMOs) are described. The disclosed G-TMOs provide substantially the same visual benefits as SV-TMOs but do not suffer from spatial artifacts such as halos and are, in addition, computationally efficient compared to SV-TMOs. In general, G-TMOs may be identified based on application of a SV-TMO to a down-sampled version of a full-resolution input image (e.g., a thumbnail). An optimized mapping between the SV-TMO's input and output constitutes the G-TMO. It has been unexpectedly discovered that when optimized (e.g., to minimize the error between the SV-TMO's input and output), G-TMOs so generated provide an excellent visual approximation to the SV-TMO (as applied to the full-resolution image).

公开(公告)号：US20140140615A1

公开(公告)日：2014-05-22

申请号：US13683020

申请日：2012-11-21

Applicant: APPLE INC.

Inventor： Graham D. Finlayson ,  Jakkarin Singnoo

IPC: G06K9/36

CPC classification number: G06T5/002 ,  G06T5/009 ,  G06T5/40 ,  G06T2207/10024 ,  G06T2207/20192 ,  G06T2207/20208

Abstract: Techniques to generate global tone-mapping operators (G-TMOs) that, when applied to high dynamic range images, visually approximate the use of spatially varying tone-mapping operators (SV-TMOs) are described. The disclosed G-TMOs provide substantially the same visual benefits as SV-TMOs but do not suffer from spatial artifacts such as halos and are, in addition, computationally efficient compared to SV-TMOs. In general, G-TMOs may be identified based on application of a SV-TMO to a down-sampled version of a full-resolution input image (e.g., a thumbnail). An optimized mapping between the SV-TMO's input and output constitutes the G-TMO. It has been unexpectedly discovered that when optimized (e.g., to minimize the error between the SV-TMO's input and output), G-TMOs so generated provide an excellent visual approximation to the SV-TMO (as applied to the full-resolution image).

Abstract translation: 描述了当应用于高动态范围图像时视觉上近似使用空间变化色调映射算子（SV-TMO）的生成全局色调映射算子（G-TMO）的技术。 所公开的G-TMO提供与SV-TMO基本上相同的视觉效果，但是不会像诸如光晕那样的空间伪影，而且与SV-TMO相比，计算效率更高。 通常，可以基于将SV-TMO应用于全分辨率输入图像（例如，缩略图）的下采样版本来识别G-TMO。 SV-TMO的输入和输出之间的优化映射构成了G-TMO。 已经意外地发现，当优化时（例如，为了最小化SV-TMO的输入和输出之间的误差），所生成的G-TMO提供了对SV-TMO的极好的视觉近似（应用于全分辨率图像） 。