Abstract: In machine learning, attention mechanisms are used to determine the importance of each component in a sequence relative to the other components in that sequence. Attention mechanisms enable artificial intelligence models to focus on the most relevant parts of data to provide context-aware outputs, which improves tasks such as machine translation, text summarization, image captioning, speech recognition, etc. Traditional attention models compute attention for multi-dimensional data for every possible pair of data elements in the multi-dimensional data or sequentially element-by-element, both approaches of which are computationally expensive and time-consuming. The present disclosure provides an attention mechanism that employs multi-dimensional linear propagation when computing attention information, which can improve spatial coherence and efficiency by directly operating on spatially coherent image data and forming dense pairwise connections through the multi-dimensional linear approach.

Abstract: Pre-trained world foundation models (diffusion and autoregressive) may be post trained (fine-tuned) for robotic manipulation tasks. The pre-trained world foundation models (WFMs) process video frames (observations) and a text prompt (perturbation) to generate output video corresponding to future observations based on the video frames and text prompt. The WFM generates the output video while maintaining three-dimensional consistency and physics accuracy between the input video frames and each successive frame in the output video.

Abstract: Pre-trained world foundation models (diffusion and autoregressive) may be post trained (fine-tuned) for robotic manipulation tasks. The pre-trained world foundation models (WFMs) process video frames (observations) and a text prompt (perturbation) to generate output video corresponding to future observations based on the video frames and text prompt. The WFM generates the output video while maintaining three-dimensional consistency and physics accuracy between the input video frames and each successive frame in the output video.

Abstract: Neural network architectures and machine learning techniques that support tokenization of raw visual input to generate a compact representation in a latent feature space as well as de-tokenization to generate raw visual output. In at least one embodiment, tokenization systems and methods leverages wavelet transforms and causal operations to capture spatial and temporal dependencies in the raw visual input.

Abstract: One embodiment of a method includes applying a first generator model to a semantic representation of an image to generate an affine transformation, where the affine transformation represents a bounding box associated with at least one region within the image. The method further includes applying a second generator model to the affine transformation and the semantic representation to generate a shape of an object. The method further includes inserting the object into the image based on the bounding box and the shape.

Abstract: One embodiment of a method includes applying a first generator model to a semantic representation of an image to generate an affine transformation, where the affine transformation represents a bounding box associated with at least one region within the image. The method further includes applying a second generator model to the affine transformation and the semantic representation to generate a shape of an object. The method further includes inserting the object into the image based on the bounding box and the shape.

Abstract: One embodiment of a method includes applying a first generator model to a semantic representation of an image to generate an affine transformation, where the affine transformation represents a bounding box associated with at least one region within the image. The method further includes applying a second generator model to the affine transformation and the semantic representation to generate a shape of an object. The method further includes inserting the object into the image based on the bounding box and the shape.

Abstract: One embodiment of a method includes applying a first generator model to a semantic representation of an image to generate an affine transformation, where the affine transformation represents a bounding box associated with at least one region within the image. The method further includes applying a second generator model to the affine transformation and the semantic representation to generate a shape of an object. The method further includes inserting the object into the image based on the bounding box and the shape.

Abstract: A method, apparatus and device for camera calibration, and a storage medium. A camera to be calibrated for performing depth estimation on a scene is determined. A first correlation function for characterizing a correlation between a sensor modulation signal of the camera to be calibrated and a first modulated light emission signal is determined. A second correlation function for characterizing an actual correlation function produced by the camera to be calibrated is determined. A calibrated impulse response based on the first correlation function and the second correlation function is determined. The camera to be calibrated is calibrated based on the calibrated impulse response, to obtain the calibrated camera.

Abstract: A method and device for generating data and computer storage medium are provided. In the method, an original image is obtained and first depth information of the original image is determined; point spread functions for four phases matching the first depth information and a complete point spread function matching the first depth information are determined; the original image is processed according to the point spread functions for the four phases to obtain input image data, and the original image is processed according to the complete point spread function to obtain labeled image data; and the input image data and the labeled image data are determined as training data for training a neural network.

Abstract: A temporal propagation network (TPN) system learns the affinity matrix for video image processing tasks. An affinity matrix is a generic matrix that defines the similarity of two points in space. The TPN system includes a guidance neural network model and a temporal propagation module and is trained for a particular computer vision task to propagate visual properties from a key-frame represented by dense data (color), to another frame that is represented by coarse data (grey-scale). The guidance neural network model generates an affinity matrix referred to as a global transformation matrix from task-specific data for the key-frame and the other frame. The temporal propagation module applies the global transformation matrix to the key-frame property data to produce propagated property data (color) for the other frame. For example, the TPN system may be used to colorize several frames of greyscale video using a single manually colorized key-frame.

Abstract: A temporal propagation network (TPN) system learns the affinity matrix for video image processing tasks. An affinity matrix is a generic matrix that defines the similarity of two points in space. The TPN system includes a guidance neural network model and a temporal propagation module and is trained for a particular computer vision task to propagate visual properties from a key-frame represented by dense data (color), to another frame that is represented by coarse data (grey-scale). The guidance neural network model generates an affinity matrix referred to as a global transformation matrix from task-specific data for the key-frame and the other frame. The temporal propagation module applies the global transformation matrix to the key-frame property data to produce propagated property data (color) for the other frame. For example, the TPN system may be used to colorize several frames of greyscale video using a single manually colorized key-frame.

Abstract: A method and device for image processing and computer storage medium are disclosed. In the method, red-green-blue (RGB) images corresponding to a raw image are obtained by demosaicing the raw image acquired by an image sensor; input data is obtained by downsampling the RGB images; and labeled data is generated according to the RGB images; and the input data and the labeled data are determined as training data for training the neural network.

Abstract: Inverse rendering estimates physical scene attributes (e.g., reflectance, geometry, and lighting) from image(s) and is used for gaming, virtual reality, augmented reality, and robotics. An inverse rendering network (IRN) receives a single input image of a 3D scene and generates the physical scene attributes for the image. The IRN is trained by using the estimated physical scene attributes generated by the IRN to reproduce the input image and updating parameters of the IRN to reduce differences between the reproduced input image and the input image. A direct renderer and a residual appearance renderer (RAR) reproduce the input image. The RAR predicts a residual image representing complex appearance effects of the real (not synthetic) image based on features extracted from the image and the reflectance and geometry properties. The residual image represents near-field illumination, cast shadows, inter-reflections, and realistic shading that are not provided by the direct renderer.

Abstract: A method for image processing, an electronic device, and a storage medium are provided. The method includes that: an image to be processed and respective semantic category information corresponding to each of multiple regions in the image to be processed are acquired, the respective semantic category information indicates at least one semantic category corresponding to the region; a respective category mapping parameter corresponding to each of the at least one semantic category is acquired; based on the respective semantic category information corresponding to each region and the respective category mapping parameter corresponding to each semantic category, a region mapping parameter corresponding to the region is determined; and the image to be processed is processed based on region mapping parameters corresponding to respective regions to obtain a processed image.

Abstract: When a computer image is generated from a real-world scene having a semi-reflective surface (e.g. window), the computer image will create, at the semi-reflective surface from the viewpoint of the camera, both a reflection of a scene in front of the semi-reflective surface and a transmission of a scene located behind the semi-reflective surface. Similar to a person viewing the real-world scene from different locations, angles, etc., the reflection and transmission may change, and also move relative to each other, as the viewpoint of the camera changes. Unfortunately, the dynamic nature of the reflection and transmission negatively impacts the performance of many computer applications, but performance can generally be improved if the reflection and transmission are separated. The present disclosure uses deep learning to separate reflection and transmission at a semi-reflective surface of a computer image generated from a real-world scene.

Abstract: Planar regions in three-dimensional scenes offer important geometric cues in a variety of three-dimensional perception tasks such as scene understanding, scene reconstruction, and robot navigation. Image analysis to detect planar regions can be performed by a deep learning architecture that includes a number of neural networks configured to estimate parameters for the planar regions. The neural networks process an image to detect an arbitrary number of plane objects in the image. Each plane object is associated with a number of estimated parameters including bounding box parameters, plane normal parameters, and a segmentation mask. Global parameters for the image, including a depth map, can also be estimated by one of the neural networks. Then, a segmentation refinement network jointly optimizes (i.e., refines) the segmentation masks for each instance of the plane objects and combines the refined segmentation masks to generate an aggregate segmentation mask for the image.

Abstract: Techniques for estimating depth for a video stream captured by a monocular image sensor are disclosed. A sequence of image frames are captured by the monocular image sensor. A first neural network is configured to process at least a portion of the sequence of image frames to generate a depth probability volume. The depth probability volume includes a plurality of probability maps corresponding to a number of discrete depth candidate locations over a range of depths defined for the scene. The depth probability volume can be updated using a second neural network that is configured to generate adaptive gain parameters to integrate the DPVs over time. A third neural network is configured to refine the updated depth probability volume from a lower resolution to a higher resolution that matches the original resolution of the sequence of image frames. A depth map can be calculated based on the depth probability volume.

Abstract: A deep neural network (DNN) system learns a map representation for estimating a camera position and orientation (pose). The DNN is trained to learn a map representation corresponding to the environment, defining positions and attributes of structures, trees, walls, vehicles, etc. The DNN system learns a map representation that is versatile and performs well for many different environments (indoor, outdoor, natural, synthetic, etc.). The DNN system receives images of an environment captured by a camera (observations) and outputs an estimated camera pose within the environment. The estimated camera pose is used to perform camera localization, i.e., recover the three-dimensional (3D) position and orientation of a moving camera, which is a fundamental task in computer vision with a wide variety of applications in robot navigation, car localization for autonomous driving, device localization for mobile navigation, and augmented/virtual reality.

Abstract: A temporal propagation network (TPN) system learns the affinity matrix for video image processing tasks. An affinity matrix is a generic matrix that defines the similarity of two points in space. The TPN system includes a guidance neural network model and a temporal propagation module and is trained for a particular computer vision task to propagate visual properties from a key-frame represented by dense data (color), to another frame that is represented by coarse data (grey-scale). The guidance neural network model generates an affinity matrix referred to as a global transformation matrix from task-specific data for the key-frame and the other frame. The temporal propagation module applies the global transformation matrix to the key-frame property data to produce propagated property data (color) for the other frame. For example, the TPN system may be used to colorize several frames of greyscale video using a single manually colorized key-frame.