Samsung Electronics Co., Ltd.

Ruiwen Zhen

Hamid Rahim Sheikh

John W Glotzbach

Ibrahim Pekkucuksen

Long N Le

Zhen Tong

Baekdu Choi

Raja Bala

Yibo Xu

John E Glotzbach

Yuting Hu

Ibrahim E Pekkucuksen

Various image sharpening techniques are disclosed. For example, a method for image sharpening includes obtaining, using at least one sensor of an electronic device, an image that includes visual content. The method also includes generating an edge map that indicates edges of the visual content within the image. The method further includes applying a high-pass signal and an adaptive gain based on the edge map to sharpen the image. The method also includes generating a bright halo mask and a dark halo mask based on the edge map, where the bright halo mask indicates an upper sharpening limit and the dark halo mask indicates a lower sharpening limit. In addition, the method includes modifying a level of sharpening at one or more of the edges within the sharpened image to provide halo artifact reduction based on the bright halo mask and the dark halo mask.

Image sharpening

An electronic device includes at least one imaging sensor and at least one processor coupled to the at least one imaging sensor. The at least one imaging sensor is configured to capture a burst of image frames. The at least one processor is configured to generate a low-resolution image from the burst of image frames. The at least one processor is also configured to estimate a blur kernel based on the burst of image frames. The at least one processor is further configured to perform deconvolution on the low-resolution image using the blur kernel to generate a deconvolved image. In addition, the at least one processor is configured to generate a high-resolution image using super resolution (SR) on the deconvolved image.

Kernel-aware super resolution

A method includes obtaining multiple images of a scene including a first image associated with a first exposure value and a second image associated with a second exposure value. Each image includes image data in each of multiple channels of a color space, and the first exposure value is greater than the second exposure value. The method also includes decomposing each channel of each image into a base layer and a detail layer. The method further includes generating for each image, a blending weight map for the base layer and a blending weight map for the detail layer. The method includes combining each base layer and each detail layer of each channel of each image based on the blending weight map for the base layer for the image and the blending weight map for the detail layer of the image to obtain an HDR image of the scene.

Guided multi-exposure image fusion

A method includes receiving a reference input frame and a non-reference input frame; separating a luma plane for a luma channel and a chroma plane for a chroma channel for each of the reference input frame and the non-reference input frame; generating a luma frame using the luma plane; generating a chroma frame using the chroma plane in a patch-based chroma blending; and combining the luma frame and the chroma frame into an output frame.

Apparatus and method for chroma processing for multi-frame fusion

A method includes obtaining, using at least one processor of an electronic device, a high dynamic range (HDR) input Bayer image. The method also includes generating, using the at least one processor of the electronic device, a plurality of synthesized images at different exposure levels based on the input Bayer image. The method further includes fusing, using the at least one processor of the electronic device, the synthesized images to generate a fused image. The method also includes generating, using the at least one processor of the electronic device, a gain map based on the fused image. In addition, the method includes applying, using the at least one processor of the electronic device, a gain based on the gain map to the input Bayer image.

Systems and methods for dynamic range compression in multi-frame processing

A method includes obtaining, using at least one processor, an image of a scene including image data in each of multiple channels of a color space. The method also includes decomposing a channel of the image into a first base layer and a first detail layer. The method further includes generating a first enhanced detail layer by manipulating a characteristic of the first detail layer. The method also includes decomposing the first base layer into a second base layer and a second detail layer. The method further includes generating a second enhanced detail layer by manipulating a characteristic of the second detail layer. In addition, the method includes combining the first enhanced detail layer, the second enhanced detail layer, and the second base layer to obtain an enhanced image of the scene.

Single-image detail and contrast enhancement

A method includes obtaining, using at least one sensor of an electronic device, multiple image frames of a scene. The multiple image frames include a first image frame and a second image frame captured using different exposures. The method also includes excluding, using at least one processor of the electronic device, pixels in the first and second image frames based on a coarse motion map. The method further includes generating, using the at least one processor, multiple local histogram match maps based on different portions of the first and second image frames. In addition, the method includes generating, using the at least one processor, an image of the scene using the local histogram match maps.

Local histogram matching with global regularization and motion exclusion for multi-exposure image fusion

A method includes receiving a reference image and a non-reference image; dividing the reference image into a plurality of tiles; determining, using an electronic device, a motion vector map using coarse-to-fine based motion vector estimation; and generating an output frame using the motion vector map with the reference image and the non-reference image.

Apparatus and method for efficient regularized image alignment for multi-frame fusion

An electronic device, method, and computer readable medium for compositing high dynamic range frames are provided. The electronic device includes a camera, and a processor coupled to the camera. The processor registers the plurality of multi-exposure frames with a hybrid of matched features to align non-reference frames with a reference frame; generates blending maps of the plurality of multi-exposure frames to reduce moving ghost artifacts and identify local areas that are well-exposed in the plurality of multi-exposure frames; and blends the plurality of multi-exposure frames weighted by the blending maps using a two-step weight-constrained exposure fusion technique into a high dynamic range (HDR) frame.

System and method for compositing high dynamic range images

A method includes obtaining multiple image frames of a scene using at least one camera of an electronic device. The method also includes using a convolutional neural network to generate blending maps associated with the image frames. The blending maps contain or are based on both a measure of motion in the image frames and a measure of how well exposed different portions of the image frames are. The method further includes generating a final image of the scene using at least some of the image frames and at least some of the blending maps. The final image of the scene may be generated by blending the at least some of the image frames using the at least some of the blending maps, and the final image of the scene may include image details that are lost in at least one of the image frames due to over-exposure or under-exposure.

Techniques for convolutional neural network-based multi-exposure fusion of multiple image frames and for deblurring multiple image frames

A method includes obtaining multiple image frames of a scene using at least one sensor of an electronic device. The multiple image frames include a first image frame and a second image frame having a longer exposure than the first image frame. The method also includes generating a label map that identifies pixels in the multiple image frames that are to be used in an image. The method further includes generating the image of the scene using the pixels extracted from the image frames based on the label map. The label map may include multiple labels, and each label may be associated with at least one corresponding pixel and may include a discrete value that identifies one of the multiple image frames from which the at least one corresponding pixel is extracted.

Apparatus and method for high dynamic range (HDR) image creation of dynamic scenes using graph cut-based labeling

A method of generating an image from multiple cameras having different focal lengths is described. The method comprising receiving a wide image and a tele image; aligning the wide image and the tele image to overlap a common field of view; correcting for photometric differences between the wide image and the tele image; selecting a stitching seam for the wide image and the tele image; and joining the wide image and the tele image to generate a composite image, wherein a first portion of the composite image on one side of the stitching seam is from the wide image and a second portion of the composite image on the other side of the stitching seam is from the tele image. An electronic device for generating an image is also described.

Device having cameras with different focal lengths and a method of implementing cameras with different focal lengths

A method of processing image data in a composite image is described. The method comprises analyzing a multi-level blending of images of the composite image; identifying sharp transition boundary areas of the composite image; applying less attenuation for higher levels of multi-level blending of the composite image in the sharp transition boundary areas; and applying more attenuation for lower levels of multi-level blending of the composite image in the sharp transition boundary areas.

Processing image data in a composite image

A method includes obtaining, using at least one image sensor of an electronic device, multiple image frames of a scene. The multiple image frames include a plurality of short image frames at a first exposure level and a plurality of long image frames at a second exposure level longer than the first exposure level. The method also includes generating a short reference image frame and a long reference image frame using the multiple image frames. The method further includes selecting, using a processor of the electronic device, the short reference image frame or the long reference image frame as a reference frame, where the selection is based on an amount of saturated motion in the long image frame and an amount of a shadow region in the short image frame. In addition, the method includes generating a final image of the scene using the reference frame.

System and method for dynamic selection of reference image frame

A method of combining content from multiple frames with overlapping field of views is described. The method comprises identifying corresponding blocks between a first frame and a second frame of an image; and determining whether to replace at least a portion of the first frame with a corresponding portion of the second frame based on whether there is a match between the first frame and the second frame.

Growing community of inventors

Allen, TX, United States of America

Ruiwen Zhen