3d-shapes
Latent shapes
A collection of 3D shapes generated from latent factors to assess unsupervised learning methods
This repository contains the 3D shapes dataset, used in Kim, Hyunjik and Mnih, Andriy. "Disentangling by Factorising." In Proceedings of the 35th International Conference on Machine Learning (ICML). 2018. to assess the disentanglement properties of unsupervised learning methods.
135 stars
9 watching
31 forks
Language: Jupyter Notebook
last commit: 8 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 subeeshvasu/awsome_deep_geometry_learning | A curated list of resources and papers on deep learning solutions for processing 3D shapes | 341 |
 google-research/visu3d | An abstraction layer between various deep learning frameworks and your program. | 147 |
| google-deepmind/meltingpot | Assesses generalization of multi-agent reinforcement learning algorithms to novel social situations | 620 |
| google-deepmind/arnheim | A toolkit for generating collage images using neural networks and optimization algorithms | 235 |
 zhou13/shapeunity | Develops a method to reconstruct 3D wireframe models from a single image using deep learning | 69 |
 matanatz/sal | A deep learning approach to learn implicit shape representations from raw geometric data. | 89 |
 j-f-liu/geom3d | A collection of data structures and algorithms for 3D geometric modeling | 38 |
| google-deepmind/tree | A library for working with nested data structures in Python | 945 |
| google-deepmind/tapnet | A deep learning project for tracking points in video sequences | 1,306 |
 sentinal4d/cellshape | Analyzes 3D cell shape features using deep learning for cancer research | 21 |
| google-deepmind/functa | A repository containing code for a meta-learning experiment on image datasets | 149 |
 threedle/text2mesh | Generates 3D meshes based on text inputs using neural networks and differentiable rendering | 926 |
| google-deepmind/einshape | A unified reshaping library for JAX and other frameworks. | 99 |
 magnet-dl/magnet | An API that simplifies the development of deep learning architectures by providing a high-level abstraction around PyTorch. | 360 |
| google-deepmind/jraph | A lightweight library for working with graph neural networks in jax. | 1,375 |