Abstract: A method for multi-camera monocular depth estimation using pose averaging is described. The method includes determining a multi-camera photometric loss associated with a multi-camera rig of an ego vehicle. The method also includes determining a multi-camera pose consistency constraint (PCC) loss associated with the multi-camera rig of the ego vehicle. The method further includes adjusting the multi-camera photometric loss according to the multi-camera PCC loss to form a multi-camera PCC photometric loss. The method also includes training a multi-camera depth estimation model and an ego-motion estimation model according to the multi-camera PCC photometric loss. The method further includes predicting a 360° point cloud of a scene surrounding the ego vehicle according to the trained multi-camera depth estimation model and the ego-motion estimation model.

Abstract: Systems and methods for training an adapter network that adapts a model pre-trained on synthetic images to real-world data are disclosed herein. A system may include a processor and a memory in communication with the processor and having machine-readable that cause the processor to output, using a neural network, a predicted scene that includes a three-dimensional bounding box having pose information of an object, generate a rendered map of the object that includes a rendered shape of the object and a rendered surface normal of the object, and train the adapter network, which adapts the predicted scene to adjust for a deformation of the input image by comparing the rendered map to the output map acting as a ground truth.

Abstract: A method for self-calibrating alignment between image data and point cloud data utilizing a machine learning model includes receiving, with an electronic control unit, image data from a vision sensor and point cloud data from a depth sensor, implementing, with the electronic control unit, a machine learning model trained to: align the point cloud data and the image data based on a current calibration, detect a difference in alignment of the point cloud data and the image data, adjust the current calibration based on the difference in alignment, and output a calibrated embedding feature map based on adjustments to the current calibration.

Abstract: A method for generating a dense light detection and ranging (LiDAR) representation by a vision system includes receiving, at a sparse depth network, one or more sparse representations of an environment. The method also includes generating a depth estimate of the environment depicted in an image captured by an image capturing sensor. The method further includes generating, via the sparse depth network, one or more sparse depth estimates based on receiving the one or more sparse representations. The method also includes fusing the depth estimate and the one or more sparse depth estimates to generate a dense depth estimate. The method further includes generating the dense LiDAR representation based on the dense depth estimate and controlling an action of the vehicle based on identifying a three-dimensional object in the dense LiDAR representation.

Abstract: A method for depth estimation performed by a depth estimation system associated with an agent includes determining a first depth of a first image and a second depth of a second image, the first image and the second image being captured by a sensor associated with the agent. The method also includes generating a first 3D image of the first image based on the first depth, a first pose associated with the sensor, and the second image. The method further includes generating a warped depth image based on transforming the first depth in accordance with the first pose. The method also includes updating the first pose based on a second pose associated with the warped depth image and the second depth, and updating the first 3D image based on the updated first pose. The method further includes controlling an action of the agent based on the updated first 3D image.

Abstract: Described are systems and methods for self-learned label refinement of a training set. In on example, a system includes a processor and a memory having a training set generation module that causes the processor to train a model using an image as an input to the model and 2D bounding based on 3D bounding boxes as ground truths, select a first subset from predicted 2D bounding boxes previously outputted by the model, retrain the model using the image as the input and the first subset as ground truths, select a second set of predicted 2D bounding boxes previously outputted by the model, and generate the training set by selecting the 3D bounding boxes from a master set of 3D bounding boxes that have corresponding 2D bounding boxes that form the second subset.

Abstract: A method includes receiving an image of a scene, inputting the image into a trained model, determining an average depth value of the image and pixel-wise residual depth values for the image with respect to the average depth value based on an output of the model, and determining a depth map for the image by adding the average depth value to the pixel-wise residual depth values.

Abstract: A method may include receiving an image of a scene, inputting the image into a trained neural network, determining an estimated depth map for the image based on a first output of the neural network, the estimated depth map comprising a depth value for each pixel of the image, and determining a confidence level of the depth value for each pixel of the image based on a second output of the neural network.

Abstract: System, methods, and other embodiments described herein relate to training a depth model for monocular depth estimation using photometric loss masks derived from motion estimates of dynamic objects. In one embodiment, a method includes generating depth maps from images of an environment. The method includes determining motion of points within the depth maps. The method includes associating the points between the depth maps to identify an object according to a correlation of the motion for a first cluster of the points with a second cluster of the points. The method includes providing the depth maps and the object as an electronic output.

Abstract: A representation of a spatial structure of objects in an image can be determined. A mode of a neural network can be set, in response to a receipt of the image and a receipt of a facing direction of a camera that produced the image. The mode can account for the facing direction. The facing direction can include one or more of a first facing direction of a first camera disposed on a vehicle or a second facing direction of a second camera disposed on the vehicle. The neural network can be executed, in response to the mode having been set, to determine the representation of the spatial structure of the objects in the image. The representation of the spatial structure of the objects in the image can be transmitted to an automotive navigation system to determine a distance between the vehicle and a specific object in the image.

Abstract: A method for three-dimensional (3D) scene reconstruction by an agent includes estimating an ego-motion of the agent based on a current image from a sequence of images and a previous image from the sequence of images. Each image in the sequence of images may be a two-dimensional (2D) image. The method also includes estimating a depth of the current image via a depth estimation model comprising a group of encoder layers and a group of decoder layers. The method further includes generating a 3D reconstruction of the current image based on the estimated ego-motion and the estimated depth. The method still further includes controlling an action of the agent based on the 3D reconstruction.

Abstract: A method for navigating a vehicle through an environment includes assigning a first weight to each pixel associated with a dynamic object and assigning a second weight to each pixel associated with a static object. The method also includes generating a dynamic object depth estimate for the dynamic object and generating a static object depth estimate for the static object, an accuracy of the dynamic object depth estimate being greater than an accuracy of the static object depth estimate. The method still further includes generating a 3D estimate of the environment based on the dynamic object depth estimate and the static object depth estimate. The method also includes controlling an action of the vehicle based on the 3D estimate of the environment.

Abstract: A method may include receiving a first image of a scene captured by a first camera at a first time step and plurality of other images of the scene captured by a plurality of other cameras at a plurality of time steps, determining a geometric relationship between the first camera at the first time step and each of the other cameras at the plurality of time steps, determining a cost volume for the first image captured by the first camera at the first time step based on the first image, the plurality of other images, and the geometric relationship between the first camera at the first time step and each of the other cameras at the plurality of time steps, and determining a depth map for the first image based on the cost volume, the depth map comprises a depth value of each pixel of the first image.

Abstract: A method for using an artificial neural network associated with an agent to estimate depth, includes receiving, at the artificial neural network, an input image captured via a sensor associated with the agent. The method also includes upsampling, at each decoding layer of a plurality of decoding layers of the artificial neural network, decoded features associated with the input image to a resolution associated with a final output of the artificial neural network. The method further includes concatenating, at each decoding layer, the upsampled decoded features with features obtained at a convolution layer associated with a respective decoding layer. The method still further includes estimating, at a recurrent module of the artificial neural network, a depth of the input image based on receiving the concatenated upsampled decoded features from each decoding layer. The method also includes controlling an action of an agent based on the depth estimate.

Abstract: A method for keypoint matching includes determining a first set of keypoints corresponding to a current environment of the agent. The method further includes determining a second set of keypoints from a pre-built map of the current environment. The method still further includes identifying matching pairs of keypoints from the first set of keypoints and the second set of keypoints based on geometrical similarities between respective keypoints of the first set of keypoints and the second set of keypoints. The method also includes determining a current location of the agent based on the identified matching pairs of keypoints. The method further includes controlling an action of the agent based on the current location.

Abstract: Systems and methods for extracting ground plane information directly from monocular images using self-supervised depth networks are disclosed. Self-supervised depth networks are used to generate a three-dimensional reconstruction of observed structures. From this reconstruction the system may generate surface normals. The surface normals can be calculated directly from depth maps in a way that is much less computationally expensive and accurate than surface normals extraction from standard LiDAR data. Surface normals facing substantially the same direction and facing upwards may be determined to reflect a ground plane.

Abstract: A method for multi-camera monocular depth estimation using pose averaging is described. The method includes determining a multi-camera photometric loss associated with a multi-camera rig of an ego vehicle. The method also includes determining a multi-camera pose consistency constraint (PCC) loss associated with the multi-camera rig of the ego vehicle. The method further includes adjusting the multi-camera photometric loss according to the multi-camera PCC loss to form a multi-camera PCC photometric loss. The method also includes training a multi-camera depth estimation model and an ego-motion estimation model according to the multi-camera PCC photometric loss. The method further includes predicting a 360° point cloud of a scene surrounding the ego vehicle according to the trained multi-camera depth estimation model and the ego-motion estimation model.

Abstract: A method for depth estimation performed by a depth estimation system of an autonomous agent includes determining a first pose of a sensor based on a first image captured by the sensor and a second image captured by the sensor. The method also includes determining a first depth of the first image and a second depth of the second image. The method further includes generating a warped depth image based on at least the first depth and the first pose. The method still further includes determining a second pose based on the warped depth image and the second depth image. The method also includes updating the first pose based on the second pose and updating a first warped image based on the updated first pose.

Abstract: Systems and methods are provided for training a depth model to recover scale factor for self-supervised depth estimation in monocular images. According to some embodiments, a method comprises receiving an image representing a scene of an environment; deriving a depth map for the image based on a depth model, the depth map comprising depth values for pixels of the image; estimating a first scale for the image based the depth values; receiving depth data captured by a range sensor, the depth data comprising a point cloud representing the scene of the environment, the point cloud comprising depth measures; determining a second scale for the point cloud based on the depth measures; determining a scale factor based the second scale and the first scale; and updating the depth model based on the scale factor, wherein the depth model generates metrically accurate depth estimates based on the scale factor.

Abstract: Systems and methods for self-supervised depth estimation using image frames captured from a camera mounted on a vehicle comprise: receiving a first image from the camera mounted at a first location on the vehicle; receiving a second image from the camera mounted at a second location on the vehicle; predicting a depth map for the first image; warping the first image to a perspective of the camera mounted at the second location on the vehicle to arrive at a warped first image; projecting the warped first image onto the second image; determining a loss based on the projection; and updating the predicted depth values for the first image.