Abstract: Techniques and systems are provided for image processing. For instance, a process can include identifying a voxel of a voxel space corresponding to a pixel of a received image, wherein the voxel includes semantic labels, and wherein the semantic labels indicate an object in an environment corresponding to the voxel; receiving a first semantic label as a semantic seed for the pixel; segmenting the image based on the semantic seed to determine a second semantic label for the pixel; and integrating the segmented image into the voxel space.

Abstract: Disclosed are systems and techniques for image processing. For example, a computing device can generate, using a multi-task model, a segmentation output and a normal output based on image(s) of a scene and a gravity vector for the scene. The computing device can learn semantic prediction(s) based on comparing the segmentation output to at least one ground truth semantic segmentation map. The computing device can also learn normal prediction(s) based on comparing the normal output to at least one ground truth normal map. The computing device can extract a semantics normal from the semantic prediction(s) and the normal prediction(s). The computing device can optimize a regularization loss based on the semantics normal and the gravity vector for the scene by learning gravity-normal regularization(s) for the scene. The computing device can determine final semantic labels for regions of the scene based on the gravity-normal regularization(s).

Abstract: Disclosed are systems and techniques for network parameter (e.g., weight) rotation for oriented camera images. For example, a computing device can obtain an image of a scene. The image is vertically aligned with the scene. The computing device can process the image using a neural network with rotated weights. The neural network is trained using a plurality of training images to generate a plurality of weights. The plurality of training images are horizontally aligned with a reference scene. The plurality of weights are rotated to generate the rotated weights.

Abstract: Disclosed are systems and techniques for image processing. For example, a computing device can generate, using a multi-task model, a segmentation output and a normal output based on image(s) of a scene and a gravity vector for the scene. The computing device can learn semantic prediction(s) based on comparing the segmentation output to at least one ground truth semantic segmentation map. The computing device can also learn normal prediction(s) based on comparing the normal output to at least one ground truth normal map. The computing device can extract a semantics normal from the semantic prediction(s) and the normal prediction(s). The computing device can optimize a regularization loss based on the semantics normal and the gravity vector for the scene by learning gravity-normal regularization(s) for the scene. The computing device can determine final semantic labels for regions of the scene based on the gravity-normal regularization(s).

Abstract: A method of image completion comprises: constructing the image repair model and constructing a plurality of conditional generative adversarial networks according to a plurality of object types; inputting the training image corresponding to the plurality of objective types such that the plurality of conditional generative adversarial networks respectively conduct a corruption feature training; inputting the image in need of repair and respectively conducting an image repair through the plurality of conditional generative adversarial networks to generate a plurality of repaired images; and judging a reasonable probability of the plurality of repaired images through a probability analyzer, choosing an accomplished image and outputting the accomplished image through an output interface.

Abstract: A method of image completion comprises: constructing the image repair model and constructing a plurality of conditional generative adversarial networks according to a plurality of object types; inputting the training image corresponding to the plurality of objective types such that the plurality of conditional generative adversarial networks respectively conduct a corruption feature training; inputting the image in need of repair and respectively conducting an image repair through the plurality of conditional generative adversarial networks to generate a plurality of repaired images; and judging a reasonable probability of the plurality of repaired images through a probability analyzer, choosing an accomplished image and outputting the accomplished image through an output interface.