SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.13326 · 2020

PointGMM: a Neural GMM Network for Point Clouds

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
amirhertz/pointgmm canonical 4 of 8
FunctionStatusWhere it lives
apply_decay Ran amirhertz/pointgmm/options.py
code served (permissive licence) · get_code("52a2715abc17d8ce")
flatten Ran amirhertz/pointgmm/models/gm_utils.py
code served (permissive licence) · get_code("5713cab2b5071792")
is_model_clean Ran amirhertz/pointgmm/models/model_factory.py
code served (permissive licence) · get_code("64f469ab95c19274")
save_pil_image Ran amirhertz/pointgmm/eval_ae.py
code served (permissive licence) · get_code("b99e9276405bead6")
collect Not yet run amirhertz/pointgmm/process_data/files_utils.py
code served (permissive licence) · get_code("0e980c2fffa64798")
dkl Not yet run amirhertz/pointgmm/models/models_utils.py
code served (permissive licence) · get_code("aaa64336b8c6ab9c")
do_when_its_time Not yet run amirhertz/pointgmm/options.py
code served (permissive licence) · get_code("2592bf49e3f0cc56")
recursive_to Not yet run amirhertz/pointgmm/models/models_utils.py
code served (permissive licence) · get_code("3d097ffe9ca61fdb")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Point clouds are a popular representation for 3D shapes. However, they encode a particular sampling without accounting for shape priors or non-local information. We advocate for the use of a hierarchical Gaussian mixture model (hGMM), which is a compact, adaptive and lightweight representation that probabilistically defines the underlying 3D surface. We present PointGMM, a neural network that learns to generate hGMMs which are characteristic of the shape class, and also coincide with the input point cloud. PointGMM is trained over a collection of shapes to learn a class-specific prior. The hierarchical representation has two main advantages: (i) coarse-to-fine learning, which avoids converging to poor local-minima; and (ii) (an unsupervised) consistent partitioning of the input shape. We show that as a generative model, PointGMM learns a meaningful latent space which enables generating consistent interpolations between existing shapes, as well as synthesizing novel shapes. We also present a novel framework for rigid registration using PointGMM, that learns to disentangle orientation from structure of an input shape.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2003.13326")
get_code_for_paper("2003.13326")
have("2003.13326")

Connect an agent — have() is free.