Calculate decomposed Relative Positional Embeddings from :paper:`mvitv2`. https://github.com/facebookresearch/mvit/blob/19786631e330df9f3622e

Expects a torch tensor with length 2 in the last dimension. Requires the original image size in (H, W) format.

! @brief access specified array element with bounds checking Returns a reference to the element at specified location @a idx, with bounds

Generates a 2D grid of points evenly spaced in [0,1]x[0,1].

! @brief clears the contents Clears the content of a JSON value and resets it to the default value as if @ref basic_json(value_t) would h

Reset all items state. */

! @brief returns a const reverse iterator to the last element Returns a const iterator to the reverse-beginning; that is, the last elemen

! @brief returns a const reverse iterator to one before the first Returns a const reverse iterator to the reverse-end; that is, one before

! @brief dump a floating-point number Dump a given floating-point number to output stream @a o. Works internally with @a number_buffer.

order textured, mesh {obj} then mesh.ply

Convienience function to find the Median Absolute Deviation from a vector of deviations. Note that it isn't a strict median( just a quick approximatio

! For n != 0, returns k, such that pow10 := 10^(k-1) <= n < 10^k. For n == 0, returns 1 and sets pow10 := 1. */

! For a normalized diyfp w = f * 2^e, this function returns a (normalized) cached power-of-ten c = f_c * 2^e_c, such that the exponent of the product

Copied from Plenoxels Continuous learning rate decay function. Adapted from JaxNeRF The returned rate is lr_init when step=0 and lr_fina