Add a new object to the composite. Computes the necessary information and calls add_height_map

Sweep through all the scenes once and compute the maximum number of times each category occurs in any single scene.

Similar to get_nodes, but overwrites self.node instead of returning a list

Similar to get_rooms, but overwrites self.node instead of returning a list

Gets the root dir of the dataset Check env variable first, if not set, use the {code_location}/data

Search for a file containing domain sizes. If we don't find it, then compute it

Return canonical semantic frame matrix for model. Transforms from semantic frame [0,1]^3, [x,y,z] = [right,up,back] to raw model coordinate

Given a category and a modelId, return all models that are relevant to it Which is: the mirrored version of the model, plus a

Get a set of rooms from the house which satisfies a certain criteria Parameters ---------- filters (list[room_filter

Bad naming, really just getting the sin and cos of the angle of rotation.

Return log probability of given set of pairwise relative observations under arrangement priors

Return probability of pairwise observation with given category_key

Projects this OBB onto the given 1D direction vector and returns projection interval [min, max]. If vector is unnormalized, the outpu

Sample placement for given node

Stop either when continue predictor predicts stopping Or if more than 20 failed insertion has occured Or if no possible inser

Synthesizes the rooms! Parameters ---------- room_ids (list[int]): indices of the room to be synthesized, loads thei

Synthesize a single room, see synth for explanation of some most paramters

Get rid of some intermediate attributes