Abstract: A processor-implemented method including, based on a first shape of a first tensor and a second shape of a second tensor used in an operation with the first tensor, determining a broadcasting type related to an extension of the first shape and the second shape, determining respective first shape offsets for each dimension of the first shape and respective second shape offsets for each dimension of the second shape based on the broadcasting type, determining respective first tensor offsets for each dimension of the first tensor and respective second tensor offsets for each dimension of the second tensor based on the broadcasting type, the respective first shape offsets for each dimension of the first shape, and the respective second shape offsets for each dimension of the second shape, determining a first offset of a first element included in the first tensor and a second offset of a second element included in the second tensor based on the respective first tensor offsets and the respective second tensor offse

Abstract: A processor-implemented method includes determining either one or both of a first voxel and a first key point of point cloud data, and by performing feature transformation on either one or both of the first voxel and the first key point through a neural network, determining either one or both of a second voxel and a second key point of the point cloud data, wherein a voxel feature of the first voxel is different from a voxel feature of the second voxel, a key point feature of the first key point is different from a key point feature of the second key point, and either one or both of the second voxel and the second key point are used for training of the point cloud data.

Abstract: An object detection method including extracting voxel features of valid cells from voxel data corresponding to a point cloud obtained using a depth sensor, and generating object detection data using a transformer-based model for object detection based on the extracted voxel features, the valid cells including cells among a plurality of cells, included in the voxel data that includes point data, and a cell among the plurality of cells that does not include corresponding point data is not a valid cell.

Abstract: A method and apparatus for object tracking are provided, where the object tracking method includes determining box information of candidate boxes in a current image frame and similarity scores of the candidate boxes based on including a search region of the current image frame with a template image corresponding to a target object, adjusting the similarity scores of the candidate boxes using a distractor map including distractor information of a previous image frame, determining a target box corresponding to the target object and a distractor box corresponding to a distractor of the target object from the candidate boxes based on the adjusted similarity scores, and updating the distractor map based on distractor information of the current image frame according to the distractor box.

Abstract: A high-definition (HD) map-related map construction method, electronic device, and storage medium are provided. The method includes: extracting a bird's-eye view (BEV) feature map based on the data; determining map information through a hybrid decoder based on the BEV feature map and a hybrid query; and constructing an HD map corresponding to the data based on the map information, wherein the map includes a plurality of map elements each including an area formed by a plurality of coordinate points in the map, the map information comprises coordinate information and class information of the plurality of map elements, and the hybrid query includes a plurality of hybrid features each corresponding to one map element and including a point feature and an element feature. Optionally, the method may be executed using an artificial intelligence (AI) model.

Abstract: A method for (3D) object detection includes: receiving an input image with respect to a 3D space, an input point cloud with respect to the 3D space, and an input language with respect to a target object in the 3D space; using an encoding model to generate candidate image features of partial areas of the input image, a point cloud feature of the input point cloud, and a linguistic feature of the input language; selecting a target image feature corresponding to the linguistic feature from among the candidate image features based on similarity scores of similarities between the candidate image features and the linguistic feature; generating a decoding output by executing a multi-modal decoding model based on the target image feature and the point cloud feature; and detecting a 3D bounding box corresponding to the target object by executing an object detection model based on the decoding output.

Abstract: A processor-implemented method with liveness detection includes: receiving a plurality of phase images of different phases; generating a plurality of preprocessed phase images by performing preprocessing, including edge enhancement processing, on the plurality of phase images of different phases; generating a plurality of differential images based on the preprocessed phase images; generating a plurality of low-resolution differential images having lower resolutions than the differential images, based on the differential images; generating a minimum map image based on the low-resolution differential images; and performing a liveness detection on an object in the phase images based on the minimum map image.

Abstract: A method and apparatus with a feature-level ensemble model are provided. A method of operating an ensemble model based on feature-level consolidation includes: obtaining queries by inputting a same input data item to respective transformer models, the transformer models generating respective queries from the input data item; forming an ensemble query corresponding to the queries; and generating a predicted value of the input data item by applying the ensemble query to a prediction model that includes a transformer decoder, the prediction model inferring the predicted value from the ensemble query.

Abstract: An object detection method and an object detection apparatus for detecting an object based on multi-features are provided. The object detection method includes: obtaining first-sensor data from a first sensor and obtaining second-sensor data from a second sensor, wherein the first sensor is a different type of sensor than the second sensor; extracting a first feature from the first-sensor data and extracting a second feature from the second-sensor data; determining a target feature-type by inputting the first and second features to a feature-type selection model which, based thereon, predicts the target feature-type; determining a target feature to be used for object detection according to the determined target feature-type; and determining an object detection result based on the determined target feature.

Abstract: A method performed by one or more processors includes: iteratively training layer-specific quantization levels and layer-specific quantization intervals of respective layers of a neural network of original weights by, for each training iteration, adjusting the quantization levels and quantization intervals to reduce a loss that is determined based on the original weights and is determined based on the original weights as quantized according to the quantization levels and quantization intervals at a current iteration of the training.

Abstract: A processor-implemented method includes generating a preprocessed infrared (IR) image by performing first preprocessing based on an IR image including an object; generating a preprocessed depth image by performing second preprocessing based on a depth image including the object; and determining whether the object is a genuine object based on the preprocessed IR image and the preprocessed depth image.

Abstract: A target object detection method and apparatus are provided. The target object detection method and apparatus are applicable to fields such as artificial intelligence, object tracking, object detection, and image processing. An object is detected from a frame image of a video including a plurality of frame images based on a target template set including one or more target templates.

Abstract: A method performed by one or more processors of an electronic device includes: processing an input image and point cloud data corresponding to the input image; projecting the point cloud data to generate a first depth map and adding new depth values to the first depth map based on the input image; obtaining a second depth map by inputting the input image to a depth estimation model configured to infer depth maps from input images; and training the depth estimation model based on a loss difference between the first depth map and the second depth map.

Abstract: An image processing method is provided. The method includes obtaining a first bird's eye view (BEV) feature of first data, obtaining a second BEV feature of second data, inputting the first BEV feature and the second BEV feature to a self-attention network to obtain a third BEV feature of the first data and a fourth BEV feature of the second data, and obtaining a fusion feature in which the third BEV feature and the fourth BEV feature are fused, wherein the first data and the second data are collected by different sensors. Related operations of the examples provided by the present disclosure are implemented by an AI model. AI-related functions are performed by non-volatile memory, volatile memory, and a processor.

Abstract: An apparatus and method for quantizing a transformer-based target tracking model are provided. The method includes obtaining a transformer-based target tracking model including a template branch, a search branch, a stitching module, and a first transformer module, generating an optimized target tracking model by removing the stitching module from the transformer-based target tracking model and dividing the first transformer module into a second transformer module and a third transformer module, and generating a quantization model corresponding to the optimized target tracking model by quantizing the divided second transformer module independently of quantizing the divided third transformer module.

Abstract: A processor-implemented method with video processing includes: determining a first image feature of a first image of video data and a second image feature of a second image that is previous to the first image; determining a time-domain information fusion processing result by performing time-domain information fusion processing on the first image feature and the second image feature; and determining a panoptic segmentation result of the first image based on the time-domain information fusion processing result.

Abstract: A method and apparatus with image correction is provided. A processor-implemented method includes generating, using a neural network model provided an input image, an illumination map including illumination values dependent on respective color casts by one or more illuminants individually affecting each pixel of the input image, and generating a white-adjusted image by removing at least a portion of the color casts from the input image using the generated illumination map.

Abstract: A device and method with object recognition is included. In one general aspect, an electronic device includes a camera sensor configured to capture a first image of a scene, the camera sensor is configured to perform at least one type of physical camera motion relative to the electronic device, the at least one type of physical camera motion includes rolling, panning, tilting, or zooming the camera sensor relative to the electronic device, and a processor configured to control the camera sensor to perform a physical motion of the physical camera motion type based on detecting an object in the first image, acquire a second image captured using the camera sensor as adjusted based on the performed physical motion, and recognize the object in the second image.

Abstract: A method and apparatus for detecting a liveness based on a phase difference are provided. The method includes generating a first phase image based on first visual information of a first phase, generating a second phase image based on second visual information of a second phase, generating a minimum map based on a disparity between the first phase image and the second phase image, and detecting a liveness based on the minimum map.

Abstract: Disclosed is a method and apparatus for adaptive tracking of a target object. The method includes method of tracking an object, the method including estimating a dynamic characteristic of an object in an input image based on frames of the input image, determining a size of a crop region for a current frame of the input image based on the dynamic characteristic of the object, generating a cropped image by cropping the current frame based on the size of the crop region, and generating a result of tracking the object for the current frame using the cropped image.