Read and unpack the next bytes from a binary file. :param fid: :param num_bytes: Sum of combination of {2, 4, 8}, e.g. 2, 6, 16, 30, etc.

Args: tar_pose: target pose [3, 3] ref_poses: reference poses [N, 3, 3] num_select: the number of nearest views to select

:param x: img 1, [(...), 3] :param y: img 2, [(...), 3] :param mask: optional, [(...)] :return: mse score

1x1 convolution

3x3 convolution with padding

:param ray_sampler: RaySamplingSingleImage for this view :param model: {'net_coarse': , 'net_fine': , ...} :param chunk_size: number of

Reads a scene from the directory base_dir.

Args: img: np.float32 [h, w, 3] transform: Returns: transformed np.float32

:param xyz: [n_rays, n_samples, 3] :param query_camera: [1, 34], 34 = img_size(2) + intrinsics(16) + extrinsics(16) :param tr

see: src/base/reconstruction.cc void Reconstruction::ReadImagesBinary(const std::string& path) void Reconstruction::WriteImagesBi

:param ray_batch: {'ray_o': [N_rays, 3] , 'ray_d': [N_rays, 3], 'view_dir': [N_rays, 2]} :param model: {'net_coarse': , 'net_fine': } :

:param bins: tensor of shape [N_rays, M+1], M is the number of bins :param weights: tensor of shape [N_rays, M] :param N_samples: number

Fills the intrinsics matrix from view_params. Args: view_params: Dict view parameters. Returns: A 3x3 matrix representing the

Fills the world from camera transform from the view_json. Args: view_json: A dictionary of view parameters. Returns: A 4x4 tra

Initialisation for DatasetFromSampler.

calculate the angular distance between two rotation matrices (batched) :param R1: the first rotation matrix [N, 3, 3] :param R2: the seco

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

:param xyz: [..., 3] :param query_camera: [34, ] :param train_cameras: [n_views, 34] :return: [n_views, ..., 4]; The

project 3D points into cameras :param xyz: [..., 3] :param train_cameras: [n_views, 34], 34 = img_size(2) + intrinsics(16) +

draw corresponding epilines on img1 for the points in img2

:param H: image height :param W: image width :param intrinsics: 4 by 4 intrinsic matrix :param c2w: 4 by 4 camera to

:param w: pixels :param h: pixels :param vmin: min value :param vmax: max value :param cmap_name: :param label :return:

check if the pixel locations are in valid range :param pixel_locations: [..., 2] :param h: height :param w: weight

load model from existing checkpoints and return the current step :param out_folder: the directory that stores ckpts :return:

convert llff format pose to 4x4 matrix of intrinsics and extrinsics (opencv convention) Args: pose: matrix [3, 4] Returns: intrin

convert llff format pose to 4x4 matrix of intrinsics and extrinsics (opencv convention) Args: pose: matrix [3, 4] Returns: intrin

Return quaternion for rotation about axis.

Return homogeneous rotation matrix from quaternion.

:param N_rand: number of rays to be casted :return:

see: src/base/reconstruction.cc void Reconstruction::WriteCamerasBinary(const std::string& path) void Reconstruction::ReadCameras

see: src/base/reconstruction.cc void Reconstruction::WriteCamerasText(const std::string& path) void Reconstruction::ReadCamerasTe

see: src/base/reconstruction.cc void Reconstruction::ReadImagesText(const std::string& path) void Reconstruction::WriteImagesText

see: src/base/reconstruction.cc void Reconstruction::ReadPoints3DText(const std::string& path) void Reconstruction::WritePoints3D

see: src/base/reconstruction.cc void Reconstruction::ReadPoints3DBinary(const std::string& path) void Reconstruction::WritePoints

:param ray_o: origin of the ray in scene coordinate system; tensor of shape [N_rays, 3] :param ray_d: homogeneous ray direction vectors in sc