| 发明名称 |
METHOD AND SYSTEM FOR DENOISING IMAGES USING DEEP GAUSSIAN CONDITIONAL RANDOM FIELD NETWORK |
| 摘要 |
A sensor acquires an input image X of a scene. The image includes noise with a variance σ2. A deep Gaussian conditional random field (GCRF) network is applied to the input image to produce an output image Y, where the output image is denoised, and wherein the deep GCRF includes a prior generation (PgNet) network followed by an inference network (InfNet), wherein the PgNet produces patch covariance priors Σij for patches centered on every pixel (i,j) in the input image, and wherein the InfNet is applied to the patch covariance priors and the input image to solve the GCRF. |
| 申请公布号 |
US2017076170(A1) |
申请公布日期 |
2017.03.16 |
| 申请号 |
US201514854352 |
申请日期 |
2015.09.15 |
| 申请人 |
Mitsubishi Electric Research Laboratories, Inc. |
发明人 |
Tuzel Oncel;Liu Ming-Yu;Vemulapalli Raviteja |
| 分类号 |
G06K9/40;G06N3/08;G06K9/62 |
主分类号 |
G06K9/40 |
| 代理机构 |
|
代理人 |
|
| 主权项 |
1. A method for denoising an image, comprising steps of:
acquiring an input image X, wherein the input image includes noise with a variance σ2; and applying a deep Gaussian conditional random field (GCRF) network to the input image to produce an output image Y, where the output image is denoised, and wherein the deep GCRF includes a prior generation (PgNet) network followed by an inference network (InfNet), wherein the PgNet produces patch covariance priors Σij for patches centered on every pixel (i,j) in the input image, and wherein the InfNet is applied to the patch covariance priors and the input image to solve the GCRF, wherein the applying is performed in a processor. |
| 地址 |
Cambridge MA US |
