RAPNet with EB0 backbone, feature levels can be customized

Convenience class to aply the same operation to a whole set of images.

Lie algebra for SO(3) and SE(3) operations in PyTorch

MLP as used in Vision Transformer, MLP-Mixer and related networks

Small adaptation layers.

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

Interpolation module.

DPT module for CroCo. by default, hooks_idx will be equal to: * for encoder-only: 4 equally spread layers * for encoder+decoder: last enc

A simple MLP to regress a pose component

Residual convolution module.

Track a series of values and provide access to smoothed values over a window or the global series average.

Random sampling under a constraint: each sample in the batch has the same feature, which is chosen randomly from a known pool of 'features' for

Dataset of outdoor street scenes, 5 images each time

A class to represent camera pose loss.

Concatenation of several datasets

Mixture between MLP and DPT head that outputs 3d points and local features (with MLP). The input for both heads is a concatenation of Encoder and

DPT output adapter. :param num_cahnnels: Number of output channels :param stride_level: tride level compared to the full-sized image.

Adapt croco's DPTOutputAdapter implementation for dust3r: remove duplicated weigths, and fix forward for dust3r

Early stops the training if validation criteria doesn't improve after a given patience.

Feature fusion block.

Symmetric InfoNCE loss with in-batch negatives.

Euclidean distance between 3d points

Linear head for dust3r Each token outputs: - 16x16 3D points (+ confidence)

Optimize a global scene, given a list of pairwise observations. Unlike PointCloudOptimizer, you can fix parts of the optimization process (partia

Artifically augmenting the size of a dataset.

This a Dummy Optimizer. To use only when the goal is to visualize the results for a pair of images (with is_symmetrized)

just adding _init_weights + position getter compared to timm.models.layers.patch_embed.PatchEmbed

DPT module for dust3r, can return 3D points + confidence for all pixels

Optimize a global scene, given a list of pairwise observations. Graph node: images Graph edges: observations = (pred1, pred2)

Absolute pos embedding, learned.

Absolute pos embedding, learned.

return positions of patches

random masking

Artifically changing the size of a dataset.