set iterator to a defined past the end

Transfer some variables to another device (i.e. GPU, CPU:torch, CPU:numpy). batch: list, tuple, dict of tensors or other things device: pyto

method to write out image Args: name: data identifier image: rendered image to write step: the time step

! @param[in] j JSON value to serialize @param[in] use_count whether to use '#' prefixes (optimized format) @param[in] use_type wheth

Init. Args: scale_factor (float): scaling mode (str): interpolation mode

return_all_blocks: if True, return the features at the end of every block instead of just the features from the l

Gets the camera object from the viewer and updates the movement state if it has changed.

Draw an image using the current camera pose from the viewer. The image is sent of a TCP connection and then uses WebRTC to send it to

@brief returns a const iterator to the first element @sa https://json.nlohmann.me/api/basic_json/cbegin/

property: colorAttachments

method: commandBuffer

Download specific captures a given dataset and capture name.

method: drawIndexedPrimitives:indexCount:indexType:indexBuffer:indexBufferOffset:instanceCount:

Args: errors (list): [N,] thresholds (list)

Apply bilateral filter to an input x

Retrieve the base directory to set relative paths

Set everything in the dict to the specified torch device. Args: stuff: things to convert to torch device: machine to put the "stu

Utility function to read a mask image from the given path and return a boolean tensor

Return weights based on predicted alphas Args: alphas: Predicted alphas (maybe from sdf) for samples along ray Returns:

compute the gradient of the ray

@brief return whether value is a floating-point number @sa https://json.nlohmann.me/api/basic_json/is_number_float/

Load the checkpoint from the given path Args: loaded_state: pre-trained model state dict

build a prediction head for the decoder

Merge two set of ray samples and return sorted index which can be used to merge sdf values Args: ray_samples_1 : ray_samples to m

Setter function to place scalars into the queue to be written out Args: name: name of scalar scalar: value step: step ass

Convert ray samples to s space

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

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

extract confidence from prediction head output

method: renderCommandEncoderWithDescriptor:

Run a command kill actions if it fails Args: command: command to run continue_on_fail: whether to continue running commands if th

Run a command kill actions if it fails Args: command: command to run

Save the model and optimizers Args: step: number of steps in training for given checkpoint

method: setObject:atIndexedSubscript:

set iterator to a defined beginning

Set input dimension of Field Head

property: texture

Returns a json object from the Python object.

Predict in the correct aspect-ratio, then transpose the result in landscape and stack everything back together.

! @brief unget current character (read it again on next get) We implement unget by setting variable next_unget to true. The input is not