Learning to generate synthetic datasets for training neural networks

    公开(公告)号:US11610115B2

    公开(公告)日:2023-03-21

    申请号:US16685795

    申请日:2019-11-15

    Abstract: In various examples, a generative model is used to synthesize datasets for use in training a downstream machine learning model to perform an associated task. The synthesized datasets may be generated by sampling a scene graph from a scene grammar—such as a probabilistic grammar—and applying the scene graph to the generative model to compute updated scene graphs more representative of object attribute distributions of real-world datasets. The downstream machine learning model may be validated against a real-world validation dataset, and the performance of the model on the real-world validation dataset may be used as an additional factor in further training or fine-tuning the generative model for generating the synthesized datasets specific to the task of the downstream machine learning model.

    IMAGE SYNTHESIS USING ONE OR MORE NEURAL NETWORKS

    公开(公告)号:US20220237838A1

    公开(公告)日:2022-07-28

    申请号:US17159977

    申请日:2021-01-27

    Abstract: Apparatuses, systems, and techniques are presented to synthesize representations. In at least one embodiment, one or more neural networks are used to generate one or more representations of one or more objects based, at least in part, upon one or more structural features and one or more appearance features for the one or more objects.

    Guided hallucination for missing image content using a neural network

    公开(公告)号:US10922793B2

    公开(公告)日:2021-02-16

    申请号:US16353195

    申请日:2019-03-14

    Abstract: Missing image content is generated using a neural network. In an embodiment, a high resolution image and associated high resolution semantic label map are generated from a low resolution image and associated low resolution semantic label map. The input image/map pair (low resolution image and associated low resolution semantic label map) lacks detail and is therefore missing content. Rather than simply enhancing the input image/map pair, data missing in the input image/map pair is improvised or hallucinated by a neural network, creating plausible content while maintaining spatio-temporal consistency. Missing content is hallucinated to generate a detailed zoomed in portion of an image. Missing content is hallucinated to generate different variations of an image, such as different seasons or weather conditions for a driving video.

    SEMANTIC IMAGE SYNTHESIS FOR GENERATING SUBSTANTIALLY PHOTOREALISTIC IMAGES USING NEURAL NETWORKS

    公开(公告)号:US20200242771A1

    公开(公告)日:2020-07-30

    申请号:US16258322

    申请日:2019-01-25

    Abstract: A user can create a basic semantic layout that includes two or more regions identified by the user, each region being associated with a semantic label indicating a type of object(s) to be rendered in that region. The semantic layout can be provided as input to an image synthesis network. The network can be a trained machine learning network, such as a generative adversarial network (GAN), that includes a conditional, spatially-adaptive normalization layer for propagating semantic information from the semantic layout to other layers of the network. The synthesis can involve both normalization and de-normalization, where each region of the layout can utilize different normalization parameter values. An image is inferred from the network, and rendered for display to the user. The user can change labels or regions in order to cause a new or updated image to be generated.

    System and method for optical flow estimation

    公开(公告)号:US10424069B2

    公开(公告)日:2019-09-24

    申请号:US15942213

    申请日:2018-03-30

    Abstract: A method, computer readable medium, and system are disclosed for estimating optical flow between two images. A first pyramidal set of features is generated for a first image and a partial cost volume for a level of the first pyramidal set of features is computed, by a neural network, using features at the level of the first pyramidal set of features and warped features extracted from a second image, where the partial cost volume is computed across a limited range of pixels that is less than a full resolution of the first image, in pixels, at the level. The neural network processes the features and the partial cost volume to produce a refined optical flow estimate for the first image and the second image.

Patent Agency Ranking