Method: 1) express all 3d points in each camera coordinate frame 2) if they're in front of a depthmap --> then lower their confidence

Modify camera intrinsics to follow a different convention. Coordinates of the center of the top-left pixels are by default: - (0.5, 0.5)

Photometric augmentation

Args: x: np.ndarray, [H, W, D]

turn a grayscale image into a color image :param x: input grayscale, [H, W] :param cmap_name: the colorization method :param mask: th

turn a grayscale image into a color image :param x: input grayscale, [H, W] :param cmap_name: the colorization method :param mask: th

turn a grayscale image into a color image :param x: input grayscale, [H, W] :param cmap_name: the colorization method :param mask: th

turn a grayscale image into a color image :param x: input grayscale, [H, W] :param cmap_name: the colorization method :param mask: th

edges: 'i_j', (i,j)

Compute a HxWx3 pointmap in camera frame from a HxW depth map.

Compute the 4x4 pose matrix by inverting the 3x4 extrinsic matrix (plus a row [0, 0, 0, 1]). Args: extrinsics_array (np.ndarray): A

Convert normalized device coordinates to a pinhole camera intrinsic matrix.

Create a commandline string to generate a scene.

return PixelwiseTaskWithDPT for given net params

Read depth data from file, return as numpy array.

Args: - depthmap (HxW array): - camera_intrinsics: a 3x3 matrix Returns: pointmap of absolute coordinates (HxWx3 arra

dnames: list of datasets with image pairs, separated by +

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

run encoder for a pair of images it is actually ~5% faster to concatenate the images along the batch dimension than to encode them se

Reprojection method, for when the absolute depth is known: 1) estimate the camera focal using a robust estimator 2) reproject points onto true

Read an OpenEXR file and return an HDR image as a NumPy array.

flow_utils.flowMaxNorm(flow): return the maximum of the l2-norm of the given flow ---- PARAMETERS ---- flow: the flow ---- OUTPU

flow_utils.flowToColor(flow): return a color code flow field, normalized based on the maximum l2-norm of the flow flow_utils.flowToColor(flow

Converts field of view (FOV) in degrees to a camera intrinsic matrix. Args: width (int): Image width in pixels. height (int)

Generate tuples of overlapping views for a given scene. generate_depth: generate depth images and camera parameters.

Generate images from a metadata file for reproducibility purposes.