Abstract: A unified place recognition framework handles both retrieval and re-ranking with a unified transformer model. The re-ranking modules utilizes feature correlation, attention value, and x/y coordinates into account, and learns to determine whether an image pair is from a same location.

Abstract: The present disclosure describes techniques for processing monocular videos using three-dimensional gaussian splatting (3DGS). Spatial decomposition and temporal decomposition are performed on a monocular video to generate a plurality of clips. A first set of 3DGS representing foreground objects in each of the plurality of clips are initialized and optimized. A second set of 3DGS representing background in each of the plurality of clips are initialized and optimized. Two images are generated for each frame comprised in each of the plurality of clips based on the first set of 3DGS and the second set of 3DGS, respectively. Two images are merged to generate a resulting image for each frame in each of the plurality of clips. The resulting image accurately represents a corresponding frame in the monocular video.

Abstract: Embodiments of the disclosure provide a method and a device for processing a portrait image, the method includes: acquiring a to-be-processed portrait image; inputting the to-be-processed portrait image into an image processing model, and acquiring a head smear image output by the image processing model, where the image processing model is configured to smear a hair area of a portrait located above a preset boundary in the portrait image, and the image processing model is generated by training a sample data set of a sample portrait image and a sample head smear image corresponding to the sample portrait image; rendering the head smear image with a head effect material to obtain a portrait image added with an effect; and displaying the portrait image added with the effect.

Abstract: Embodiments of the present disclosure provide an image processing method and apparatus, an electronic device and a storage medium. The method includes: obtaining an image to be processed; and inputting the image to be processed to an image attribute parameter changing model to obtain a target image, where a target attribute parameter value of the target image is different from a target attribute parameter value of the image to be processed, and the target attribute parameter value of the target image and the target attribute parameter value of the image to be processed correspond to different target attribute representation states.

Abstract: The present disclosure describes techniques for generating latent representations of images using a machine learning model. An image is split and flattened into a series of patches. The series of patches is concatenated with a sequence of latent tokens. The concatenated patches and latent tokens are input into an encoder of the machine learning model. A one-dimensional (1D) latent representation of the image is generated by the encoder. Vector quantization is performed on the 1D latent representation of the image by a vector quantizer of the machine learning model to generate quantized latent tokens. The image is reconstructed based on the quantized latent tokens by a decoder of the machine learning model.

Abstract: A method and an apparatus for image processing, electronic device and a storage medium are configured for: obtaining an image to be processed that is an image with a preset object, respective portions of pixels of the preset object are respectively located in and outside a subject contour region in the image to be processed; obtaining a target image by inputting the image to be processed to a preset object removal processing model, the target image is an object removal image corresponding to the image with the preset object; the model trained on a pre-established set of image sample pairs without the preset object, wherein each image sample pair comprises an original image with a preset object, and a preset object removal image obtained by processing respective pixels of a preset object respectively located outside and in the subject contour region in the original image.

Abstract: Single-stage frameworks for open-vocabulary panoptic segmentation are provided.

Abstract: The present disclosure provides an image processing method, an apparatus, an electronic device and a storage medium. The image processing method comprises: obtaining an original image of a target object to be processed, wherein the preset elements in the original image are displayed in a first display form; inputting the original image into a pre-trained element removal processing model to obtain a preset element removal image for the target object, and matching the preset element removal image with a template image corresponding to the preset element displayed in a second display form based on the preset attribute parameters of the target object; inputting the preset element removal image, the template image and the mask image of the preset element in the template image into a preset image element migration model to obtain a target image for the target object.

Abstract: The present disclosure describes techniques for implementing video segmentation. A video is divided into a plurality of clips. Each of the plurality of clips comprises several frames. Axial-trajectory attention is applied to each of the plurality of clips by a first sub-model. Clip features corresponding to each of the plurality of clips are generated by the first sub-model. A set of object queries corresponding to each of the plurality of clips is generated based on the clip features by a transformer decoder. Trajectory attention is applied to refine sets of object queries corresponding to the plurality of clips by a second sub-model. Video-level segmentation results are generated based on the refined object queries.

Abstract: The present disclosure describes techniques for processing monocular videos using three-dimensional gaussian splatting (3DGS). Spatial decomposition and temporal decomposition are performed on a monocular video to generate a plurality of clips. A first set of 3DGS representing foreground objects in each of the plurality of clips are initialized and optimized. A second set of 3DGS representing background in each of the plurality of clips are initialized and optimized. Two images are generated for each frame comprised in each of the plurality of clips based on the first set of 3DGS and the second set of 3DGS, respectively. Two images are merged to generate a resulting image for each frame in each of the plurality of clips. The resulting image accurately represents a corresponding frame in the monocular video.

Abstract: An example method for verifying data integrity in a storage system includes detecting a write command that initiates a data storage operation, wherein the data storage operation includes processing data via a data storage path from intake of the data into the storage system to storing the data in a storage device of the storage system, the data storage path comprising at least a first processing stage and a second processing stage; generating, based on a first intermediate representation of the data produced by the first processing stage, a checksum; verifying, prior to the second processing stage producing a second intermediate representation of the data, the checksum; and directing, based on the verifying the checksum, the second processing stage to produce the second intermediate representation of the data based on the first intermediate representation of the data.

Abstract: An example method for verifying data integrity in a storage system includes detecting a data access operation that processes data via a data path between a client and a storage device of the storage system, the data path including at least a first and a second processing stage; generating, based on the data access operation, a first instance of a first checksum at a first time based on a first intermediate representation of the data; generating, a second instance of the first checksum at a second time; modifying, based on the second checksum being different from the first checksum, the first intermediate representation to generate a corrected first intermediate representation; generating, based on the corrected first intermediate representation, a third checksum; and directing, based on verifying that the third checksum matches the first checksum, the second processing stage to generate the second intermediate representation.

Abstract: Methods and systems for generating a feature map from an image is disclosed. The vision system includes a vision model or processing the image to generate the feature map according a neural network. The vision model includes a first convolutional block for downsampling a set of image data to obtain a first stage convoluted data; a second convolutional block for downsampling the first stage convoluted data to obtain a second stage convoluted data, wherein one or both of the first convolutional block and the second convolutional block is a mobile convolution block (MBConv) that includes: a first Gaussian Error Linear Unit (GELU) layer, a depth-wise convolution (DWConv) layer having, and a resizing convolution layer; and a transformer block (TFB) generating the feature map from the second stage convoluted data.

Abstract: Methods and systems are provided for generating enhanced image. A neural network system is trained where the training includes training a first neural network that generates enhanced images conditioned on content of an image undergoing enhancement and training a second neural network that designates realism of the enhanced images generated by the first neural network. The neural network system is trained by determine loss and accordingly adjusting the appropriate neural network(s). The trained neural network system is used to generate an enhanced aesthetic image from a selected image where the output enhanced aesthetic image has increased aesthetics when compared to the selected image.

Abstract: A computing system including one or more processing devices configured to receive an image. The processing devices are further configured to compute a segmentation mask that identifies a region of interest included in the image. At a feature extractor, the processing devices are further configured to compute encoded image features based on the image. The processing devices are further configured to receive a text instruction. At a visual resampler, the processing devices are further configured to compute a mask query based on the segmentation mask, the encoded image features, and the text instruction. At a generative language model, the processing devices are further configured to receive a natural language query that includes the mask query and the text instruction. Based on the natural language query, at the generative language model, the processing devices are further configured to generate and output a semantic label associated with the region of interest.

Abstract: The present disclosure describes techniques for implementing video segmentation. A video is divided into a plurality of clips. Each of the plurality of clips comprises several frames. Axial-trajectory attention is applied to each of the plurality of clips by a first sub-model. Clip features corresponding to each of the plurality of clips are generated by the first sub-model. A set of object queries corresponding to each of the plurality of clips is generated based on the clip features by a transformer decoder. Trajectory attention is applied to refine sets of object queries corresponding to the plurality of clips by a second sub-model. Video-level segmentation results are generated based on the refined object queries.

Abstract: Provided in the embodiments of the present disclosure are a video processing method and device. The video processing method includes: determining a target image to be processed in a video; performing semantic segmentation on the target image through a convolutional neural network to obtain a first feature map, wherein the first feature map comprises a feature map corresponding to at least one semantic class; determining a target image region corresponding to the at least one semantic class in the target image according to the first feature map; wherein the at least one semantic class comprises an object-in-hand, and a training image adopted by the convolutional neural network in a training process is marked with an image region corresponding to the at least one semantic class.

Abstract: Provided are a transition type determination method, an electronic device and a storage medium. The method includes: acquiring a picture matching degree between a candidate transition type and a transition position of two adjacent video clips, and acquiring a music matching degree of the candidate transition type and background music of a video to which the two adjacent video clips belong; and determining a target transition type for the transition position according to the picture matching degree and the music matching degree, where the target transition type is used for a transition effect between the two adjacent video clips.

Abstract: The embodiments of the present disclosure provide a video generation method, an apparatus, a device, and a storage medium, the video generation method including: obtaining a plurality of images and music matched to the plurality of images; determining first feature information for the plurality of images and second feature information for the music; according to the first feature information, the second feature information and a plurality of pre-stored rendering effects, determining a target rendering effect combination; the rendering effects being animation, special effects or a transition; and generating a video according to the plurality of images, the music and the target rendering effect combination.

Abstract: The present disclosure provides an image processing method and device. The image processing method includes: performing, by an encoder and a first model, multiple iterations on an initial image to obtain a target image feature corresponding to the initial image; and performing, by a second model, image reconstruction based on the target image feature to obtain a reconstructed image of the initial image, both of the first model and the second model being neural networks for image reconstruction, wherein in the multiple iterations, an image feature extracted by the first model in the image reconstruction and an output image of the first model are feedback information for the encoder to assist the encoder in encoding the initial image.