Techniques related to implementing fully convolutional networks for semantic image segmentation are discussed. Such techniques may include combining feature maps from multiple stages of a multi-stage fully convolutional network to generate a hyper-feature corresponding to an input image, up-sampling the hyper-feature and summing it with a feature map of a previous stage to provide a final set of features, and classifying the final set of features to provide semantic image segmentation of the input image.

Techniques related to implementing fully convolutional networks for semantic image segmentation are discussed. Such techniques may include combining feature maps from multiple stages of a multi-stage fully convolutional network to generate a hyper-feature corresponding to an input image, up-sampling the hyper-feature and summing it with a feature map of a previous stage to provide a final set of features, and classifying the final set of features to provide semantic image segmentation of the input image.

Methods for automated segmentation system for retinal blood vessels from optical coherence tomography angiography images include a preprocessing stage, an initial segmentation stage, and a refining stage. Application of machine-learning techniques to segmented images allow for automated diagnosis of retinovascular diseases, such as diabetic retinopathy.

Methods for automated segmentation system for retinal blood vessels from optical coherence tomography angiography images include a preprocessing stage, an initial segmentation stage, and a refining stage. Application of machine-learning techniques to segmented images allow for automated diagnosis of retinovascular diseases, such as diabetic retinopathy.

Embodiments described herein provide a system for generating semantically accurate synthetic images. During operation, the system generates a first synthetic image using a first artificial intelligence (AI) model and presents the first synthetic image in a user interface. The user interface allows a user to identify image units of the first synthetic image that are semantically irregular. The system then obtains semantic information for the semantically irregular image units from the user via the user interface and generates a second synthetic image using a second AI model based on the semantic information. The second synthetic image can be an improved image compared to the first synthetic image.

Embodiments described herein provide a system for generating semantically accurate synthetic images. During operation, the system generates a first synthetic image using a first artificial intelligence (AI) model and presents the first synthetic image in a user interface. The user interface allows a user to identify image units of the first synthetic image that are semantically irregular. The system then obtains semantic information for the semantically irregular image units from the user via the user interface and generates a second synthetic image using a second AI model based on the semantic information. The second synthetic image can be an improved image compared to the first synthetic image.

A method for segmentation of a point cloud includes receiving a first frame of point cloud from a sensor; segmenting the first frame of point cloud to obtain a first set of point clusters representing a segmentation result for the first frame of point cloud; receiving a second frame of point cloud from the sensor; mapping the first set of point clusters to the second frame of point cloud; determining points within the second frame of point cloud which do not belong to the mapped first set of point clusters; segmenting the points within the second frame of point cloud which do not belong to the mapped first set of point clusters to obtain a second set of point clusters; and generating a segmentation result for the second frame of point cloud by combining the first set of point clusters and the second set of point clusters.

A method for segmentation of a point cloud includes receiving a first frame of point cloud from a sensor; segmenting the first frame of point cloud to obtain a first set of point clusters representing a segmentation result for the first frame of point cloud; receiving a second frame of point cloud from the sensor; mapping the first set of point clusters to the second frame of point cloud; determining points within the second frame of point cloud which do not belong to the mapped first set of point clusters; segmenting the points within the second frame of point cloud which do not belong to the mapped first set of point clusters to obtain a second set of point clusters; and generating a segmentation result for the second frame of point cloud by combining the first set of point clusters and the second set of point clusters.

Methods and systems are provided for optimal segmentation of an image based on multiple segmentations. In particular, multiple segmentation methods can be combined by taking into account previous segmentations. For instance, an optimal segmentation can be generated by iteratively integrating a previous segmentation (e.g., using an image segmentation method) with a current segmentation (e.g., using the same or different image segmentation method). To allow for optimal segmentation of an image based on multiple segmentations, one or more neural networks can be used. For instance, a convolutional RNN can be used to maintain information related to one or more previous segmentations when transitioning from one segmentation method to the next. The convolutional RNN can combine the previous segmentation(s) with the current segmentation without requiring any information about the image segmentation method(s) used to generate the segmentations.

Methods and systems are provided for optimal segmentation of an image based on multiple segmentations. In particular, multiple segmentation methods can be combined by taking into account previous segmentations. For instance, an optimal segmentation can be generated by iteratively integrating a previous segmentation (e.g., using an image segmentation method) with a current segmentation (e.g., using the same or different image segmentation method). To allow for optimal segmentation of an image based on multiple segmentations, one or more neural networks can be used. For instance, a convolutional RNN can be used to maintain information related to one or more previous segmentations when transitioning from one segmentation method to the next. The convolutional RNN can combine the previous segmentation(s) with the current segmentation without requiring any information about the image segmentation method(s) used to generate the segmentations.