Hugging Face's logo

Transformers documentation

Prompt Depth Anything

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Prompt Depth Anything

Overview

The Prompt Depth Anything model was introduced in Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation by Haotong Lin, Sida Peng, Jingxiao Chen, Songyou Peng, Jiaming Sun, Minghuan Liu, Hujun Bao, Jiashi Feng, Xiaowei Zhou, Bingyi Kang.

The abstract from the paper is as follows:

Prompts play a critical role in unleashing the power of language and vision foundation models for specific tasks. For the first time, we introduce prompting into depth foundation models, creating a new paradigm for metric depth estimation termed Prompt Depth Anything. Specifically, we use a low-cost LiDAR as the prompt to guide the Depth Anything model for accurate metric depth output, achieving up to 4K resolution. Our approach centers on a concise prompt fusion design that integrates the LiDAR at multiple scales within the depth decoder. To address training challenges posed by limited datasets containing both LiDAR depth and precise GT depth, we propose a scalable data pipeline that includes synthetic data LiDAR simulation and real data pseudo GT depth generation. Our approach sets new state-of-the-arts on the ARKitScenes and ScanNet++ datasets and benefits downstream applications, including 3D reconstruction and generalized robotic grasping.

drawing Prompt Depth Anything overview. Taken from the original paper.

Usage example

The Transformers library allows you to use the model with just a few lines of code:

>>> import torch
>>> import requests
>>> import numpy as np

>>> from PIL import Image
>>> from transformers import AutoImageProcessor, AutoModelForDepthEstimation

>>> url = "https://github.com/DepthAnything/PromptDA/blob/main/assets/example_images/image.jpg?raw=true"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> image_processor = AutoImageProcessor.from_pretrained("depth-anything/prompt-depth-anything-vits-hf")
>>> model = AutoModelForDepthEstimation.from_pretrained("depth-anything/prompt-depth-anything-vits-hf")

>>> prompt_depth_url = "https://github.com/DepthAnything/PromptDA/blob/main/assets/example_images/arkit_depth.png?raw=true"
>>> prompt_depth = Image.open(requests.get(prompt_depth_url, stream=True).raw)
>>> # the prompt depth can be None, and the model will output a monocular relative depth.

>>> # prepare image for the model
>>> inputs = image_processor(images=image, return_tensors="pt", prompt_depth=prompt_depth)

>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> # interpolate to original size
>>> post_processed_output = image_processor.post_process_depth_estimation(
...     outputs,
...     target_sizes=[(image.height, image.width)],
... )

>>> # visualize the prediction
>>> predicted_depth = post_processed_output[0]["predicted_depth"]
>>> depth = predicted_depth * 1000 
>>> depth = depth.detach().cpu().numpy()
>>> depth = Image.fromarray(depth.astype("uint16")) # mm

Resources

A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with Prompt Depth Anything.

If you are interested in submitting a resource to be included here, please feel free to open a Pull Request and we’ll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.

PromptDepthAnythingConfig

class transformers.PromptDepthAnythingConfig

< >

( backbone_config = None backbone = None use_pretrained_backbone = False use_timm_backbone = False backbone_kwargs = None patch_size = 14 initializer_range = 0.02 reassemble_hidden_size = 384 reassemble_factors = [4, 2, 1, 0.5] neck_hidden_sizes = [48, 96, 192, 384] fusion_hidden_size = 64 head_in_index = -1 head_hidden_size = 32 depth_estimation_type = 'relative' max_depth = None **kwargs )

Parameters

  • backbone_config (Union[Dict[str, Any], PretrainedConfig], optional) — The configuration of the backbone model. Only used in case is_hybrid is True or in case you want to leverage the AutoBackbone API.
  • backbone (str, optional) — Name of backbone to use when backbone_config is None. If use_pretrained_backbone is True, this will load the corresponding pretrained weights from the timm or transformers library. If use_pretrained_backbone is False, this loads the backbone’s config and uses that to initialize the backbone with random weights.
  • use_pretrained_backbone (bool, optional, defaults to False) — Whether to use pretrained weights for the backbone.
  • use_timm_backbone (bool, optional, defaults to False) — Whether or not to use the timm library for the backbone. If set to False, will use the AutoBackbone API.
  • backbone_kwargs (dict, optional) — Keyword arguments to be passed to AutoBackbone when loading from a checkpoint e.g. {'out_indices': (0, 1, 2, 3)}. Cannot be specified if backbone_config is set.
  • patch_size (int, optional, defaults to 14) — The size of the patches to extract from the backbone features.
  • initializer_range (float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
  • reassemble_hidden_size (int, optional, defaults to 384) — The number of input channels of the reassemble layers.
  • reassemble_factors (List[int], optional, defaults to [4, 2, 1, 0.5]) — The up/downsampling factors of the reassemble layers.
  • neck_hidden_sizes (List[str], optional, defaults to [48, 96, 192, 384]) — The hidden sizes to project to for the feature maps of the backbone.
  • fusion_hidden_size (int, optional, defaults to 64) — The number of channels before fusion.
  • head_in_index (int, optional, defaults to -1) — The index of the features to use in the depth estimation head.
  • head_hidden_size (int, optional, defaults to 32) — The number of output channels in the second convolution of the depth estimation head.
  • depth_estimation_type (str, optional, defaults to "relative") — The type of depth estimation to use. Can be one of ["relative", "metric"].
  • max_depth (float, optional) — The maximum depth to use for the “metric” depth estimation head. 20 should be used for indoor models and 80 for outdoor models. For “relative” depth estimation, this value is ignored.

This is the configuration class to store the configuration of a PromptDepthAnythingModel. It is used to instantiate a PromptDepthAnything model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the PromptDepthAnything LiheYoung/depth-anything-small-hf architecture.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

Example:

>>> from transformers import PromptDepthAnythingConfig, PromptDepthAnythingForDepthEstimation

>>> # Initializing a PromptDepthAnything small style configuration
>>> configuration = PromptDepthAnythingConfig()

>>> # Initializing a model from the PromptDepthAnything small style configuration
>>> model = PromptDepthAnythingForDepthEstimation(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

to_dict

< >

( )

Serializes this instance to a Python dictionary. Override the default to_dict(). Returns: Dict[str, any]: Dictionary of all the attributes that make up this configuration instance,

PromptDepthAnythingForDepthEstimation

class transformers.PromptDepthAnythingForDepthEstimation

< >

( config )

Parameters

  • config (PromptDepthAnythingConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

Prompt Depth Anything Model with a depth estimation head on top (consisting of 3 convolutional layers) e.g. for KITTI, NYUv2.

This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( pixel_values: FloatTensor prompt_depth: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.DepthEstimatorOutput or tuple(torch.FloatTensor)

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See DPTImageProcessor.call() for details.
  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
  • prompt_depth (torch.FloatTensor of shape (batch_size, 1, height, width), optional) — Prompt depth is the sparse or low-resolution depth obtained from multi-view geometry or a low-resolution depth sensor. It generally has shape (height, width), where height and width can be smaller than those of the images. It is optional and can be None, which means no prompt depth will be used. If it is None, the output will be a monocular relative depth. The values are recommended to be in meters, but this is not necessary.
  • return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
  • labels (torch.LongTensor of shape (batch_size, height, width), optional) — Ground truth depth estimation maps for computing the loss.

Returns

transformers.modeling_outputs.DepthEstimatorOutput or tuple(torch.FloatTensor)

A transformers.modeling_outputs.DepthEstimatorOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (PromptDepthAnythingConfig) and inputs.

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.

  • predicted_depth (torch.FloatTensor of shape (batch_size, height, width)) — Predicted depth for each pixel.

  • hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, num_channels, height, width).

    Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

  • attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, patch_size, sequence_length).

    Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The PromptDepthAnythingForDepthEstimation forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Examples:

>>> from transformers import AutoImageProcessor, AutoModelForDepthEstimation
>>> import torch
>>> import numpy as np
>>> from PIL import Image
>>> import requests

>>> url = "https://github.com/DepthAnything/PromptDA/blob/main/assets/example_images/image.jpg?raw=true"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> image_processor = AutoImageProcessor.from_pretrained("depth-anything/prompt-depth-anything-vits-hf")
>>> model = AutoModelForDepthEstimation.from_pretrained("depth-anything/prompt-depth-anything-vits-hf")

>>> prompt_depth_url = "https://github.com/DepthAnything/PromptDA/blob/main/assets/example_images/arkit_depth.png?raw=true"
>>> prompt_depth = Image.open(requests.get(prompt_depth_url, stream=True).raw)

>>> # prepare image for the model
>>> inputs = image_processor(images=image, return_tensors="pt", prompt_depth=prompt_depth)

>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> # interpolate to original size
>>> post_processed_output = image_processor.post_process_depth_estimation(
...     outputs,
...     target_sizes=[(image.height, image.width)],
... )

>>> # visualize the prediction
>>> predicted_depth = post_processed_output[0]["predicted_depth"]
>>> depth = predicted_depth * 1000.
>>> depth = depth.detach().cpu().numpy()
>>> depth = Image.fromarray(depth.astype("uint16")) # mm

PromptDepthAnythingImageProcessor

class transformers.PromptDepthAnythingImageProcessor

< >

( do_resize: bool = True size: typing.Dict[str, int] = None resample: Resampling = <Resampling.BICUBIC: 3> keep_aspect_ratio: bool = False ensure_multiple_of: int = 1 do_rescale: bool = True rescale_factor: typing.Union[int, float] = 0.00392156862745098 do_normalize: bool = True image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_pad: bool = False size_divisor: int = None prompt_scale_to_meter: float = 0.001 **kwargs )

Parameters

  • do_resize (bool, optional, defaults to True) — Whether to resize the image’s (height, width) dimensions. Can be overidden by do_resize in preprocess.
  • size (Dict[str, int] optional, defaults to {"height" -- 384, "width": 384}): Size of the image after resizing. Can be overidden by size in preprocess.
  • resample (PILImageResampling, optional, defaults to Resampling.BICUBIC) — Defines the resampling filter to use if resizing the image. Can be overidden by resample in preprocess.
  • keep_aspect_ratio (bool, optional, defaults to False) — If True, the image is resized to the largest possible size such that the aspect ratio is preserved. Can be overidden by keep_aspect_ratio in preprocess.
  • ensure_multiple_of (int, optional, defaults to 1) — If do_resize is True, the image is resized to a size that is a multiple of this value. Can be overidden by ensure_multiple_of in preprocess.
  • do_rescale (bool, optional, defaults to True) — Whether to rescale the image by the specified scale rescale_factor. Can be overidden by do_rescale in preprocess.
  • rescale_factor (int or float, optional, defaults to 1/255) — Scale factor to use if rescaling the image. Can be overidden by rescale_factor in preprocess.
  • do_normalize (bool, optional, defaults to True) — Whether to normalize the image. Can be overridden by the do_normalize parameter in the preprocess method.
  • image_mean (float or List[float], optional, defaults to IMAGENET_STANDARD_MEAN) — Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_mean parameter in the preprocess method.
  • image_std (float or List[float], optional, defaults to IMAGENET_STANDARD_STD) — Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_std parameter in the preprocess method.
  • do_pad (bool, optional, defaults to False) — Whether to apply center padding. This was introduced in the DINOv2 paper, which uses the model in combination with DPT.
  • size_divisor (int, optional) — If do_pad is True, pads the image dimensions to be divisible by this value. This was introduced in the DINOv2 paper, which uses the model in combination with DPT.
  • prompt_scale_to_meter (float, optional, defaults to 0.001) — Scale factor to convert the prompt depth to meters.

Constructs a PromptDepthAnything image processor.

preprocess

< >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']] prompt_depth: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None do_resize: typing.Optional[bool] = None size: typing.Optional[int] = None keep_aspect_ratio: typing.Optional[bool] = None ensure_multiple_of: typing.Optional[int] = None resample: typing.Optional[PIL.Image.Resampling] = None do_rescale: typing.Optional[bool] = None rescale_factor: typing.Optional[float] = None do_normalize: typing.Optional[bool] = None image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_pad: typing.Optional[bool] = None size_divisor: typing.Optional[int] = None prompt_scale_to_meter: typing.Optional[float] = None return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None data_format: ChannelDimension = <ChannelDimension.FIRST: 'channels_first'> input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None )

Parameters

  • images (ImageInput) — Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set do_rescale=False.
  • prompt_depth (ImageInput, optional) — Prompt depth to preprocess, which can be sparse depth obtained from multi-view geometry or low-resolution depth from a depth sensor. Generally has shape (height, width), where height and width can be smaller than those of the images. It’s optional and can be None, which means no prompt depth is used. If it is None, the output depth will be a monocular relative depth. It is recommended to provide a prompt_scale_to_meter value, which is the scale factor to convert the prompt depth to meters. This is useful when the prompt depth is not in meters.
  • do_resize (bool, optional, defaults to self.do_resize) — Whether to resize the image.
  • size (Dict[str, int], optional, defaults to self.size) — Size of the image after resizing. If keep_aspect_ratio is True, the image is resized to the largest possible size such that the aspect ratio is preserved. If ensure_multiple_of is set, the image is resized to a size that is a multiple of this value.
  • keep_aspect_ratio (bool, optional, defaults to self.keep_aspect_ratio) — Whether to keep the aspect ratio of the image. If False, the image will be resized to (size, size). If True, the image will be resized to keep the aspect ratio and the size will be the maximum possible.
  • ensure_multiple_of (int, optional, defaults to self.ensure_multiple_of) — Ensure that the image size is a multiple of this value.
  • resample (int, optional, defaults to self.resample) — Resampling filter to use if resizing the image. This can be one of the enum PILImageResampling, Only has an effect if do_resize is set to True.
  • do_rescale (bool, optional, defaults to self.do_rescale) — Whether to rescale the image values between [0 - 1].
  • rescale_factor (float, optional, defaults to self.rescale_factor) — Rescale factor to rescale the image by if do_rescale is set to True.
  • do_normalize (bool, optional, defaults to self.do_normalize) — Whether to normalize the image.
  • image_mean (float or List[float], optional, defaults to self.image_mean) — Image mean.
  • image_std (float or List[float], optional, defaults to self.image_std) — Image standard deviation.
  • prompt_scale_to_meter (float, optional, defaults to self.prompt_scale_to_meter) — Scale factor to convert the prompt depth to meters.
  • return_tensors (str or TensorType, optional) — The type of tensors to return. Can be one of:
    • Unset: Return a list of np.ndarray.
    • TensorType.TENSORFLOW or 'tf': Return a batch of type tf.Tensor.
    • TensorType.PYTORCH or 'pt': Return a batch of type torch.Tensor.
    • TensorType.NUMPY or 'np': Return a batch of type np.ndarray.
    • TensorType.JAX or 'jax': Return a batch of type jax.numpy.ndarray.
  • data_format (ChannelDimension or str, optional, defaults to ChannelDimension.FIRST) — The channel dimension format for the output image. Can be one of:
    • ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • ChannelDimension.LAST: image in (height, width, num_channels) format.
  • input_data_format (ChannelDimension or str, optional) — The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
    • "none" or ChannelDimension.NONE: image in (height, width) format.

Preprocess an image or batch of images.

post_process_depth_estimation

< >

( outputs: DepthEstimatorOutput target_sizes: typing.Union[transformers.utils.generic.TensorType, typing.List[typing.Tuple[int, int]], NoneType] = None ) → List[Dict[str, TensorType]]

Parameters

  • outputs (DepthEstimatorOutput) — Raw outputs of the model.
  • target_sizes (TensorType or List[Tuple[int, int]], optional) — Tensor of shape (batch_size, 2) or list of tuples (Tuple[int, int]) containing the target size (height, width) of each image in the batch. If left to None, predictions will not be resized.

Returns

List[Dict[str, TensorType]]

A list of dictionaries of tensors representing the processed depth predictions.

Converts the raw output of DepthEstimatorOutput into final depth predictions and depth PIL images. Only supports PyTorch.

< > Update on GitHub

←PoolFormer Pyramid Vision Transformer (PVT)→