FudanVI / compositional-scene-representation-toolbox
A toolbox of compositional scene representation learning methods and benchmark datasets.
☆12Updated last year
Alternatives and similar repositories for compositional-scene-representation-toolbox:
Users that are interested in compositional-scene-representation-toolbox are comparing it to the libraries listed below
- PyTorch re-implementation of Multi-Object Representation Learning with Iterative Variational Inference☆59Updated 2 years ago
- Pytorch Implementation of paper "Object-Centric Learning with Slot Attention"☆91Updated last year
- ☆41Updated last year
- Official code for Slot-Transformer for Videos (STEVE)☆49Updated 2 years ago
- Learning Long-term Visual Dynamics with Region Proposal Interaction Networks (ICLR 2021)☆112Updated 2 years ago
- [ICLR 2019] ]Unsupervised Discovery of Parts, Structure, and Dynamics☆46Updated 2 years ago
- Unsupervised learning of Object Landmarks through Conditional Image Generation☆47Updated 5 years ago
- Official Release of ICLR 2020 paper "SCALOR: Generative World Models with Scalable Object Representations"☆49Updated last year
- [NeurIPS 2021] Unsupervised Foreground Extraction via Deep Region Competition☆42Updated 3 years ago
- Official code release for the ObSuRF model☆33Updated 2 years ago
- This is the official source code for SLATE. We provide the code for the model, the training code, and a dataset loader for the 3D Shapes …☆86Updated 2 years ago
- [ICML 2020] Visual Grounding of Learned Physical Models☆39Updated 4 years ago
- CCVS: Context-aware Controllable Video Synthesis☆22Updated 3 years ago
- Official Code for Neural Systematic Binder☆32Updated 2 years ago
- Official PyTorch implementation of "SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition"☆102Updated last year
- Official Release of NeurIPS 2023 Spotlight paper "Object-Centric Slot Diffusion"☆65Updated last year
- Official PyTorch implementation of "Improving Generative Imagination in Object-Centric World Models"☆35Updated 2 years ago
- xingzhehe / AutoLink-Self-supervised-Learning-of-Human-Skeletons-and-Object-Outlines-by-Linking-Keypoints[NeurIPS 2022] AutoLink, a simple and novel unsupervised approach to detect keypoints from single static images☆48Updated last year
- This repository is the official implementation of Improving Object-centric Learning With Query Optimization☆50Updated last year
- Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns☆16Updated 2 years ago
- ☆23Updated 2 years ago
- [NeurIPS 2022] code for "Visual Concepts Tokenization"☆21Updated 2 years ago
- Slot-TTA shows that test-time adaptation using slot-centric models can improve image segmentation on out-of-distribution examples.☆26Updated last year
- [NeurIPS 2021 Spotlight] Learning to Compose Visual Relations☆102Updated last year
- ☆73Updated 2 years ago
- ☆13Updated last week
- Personal Python toolbox☆16Updated 9 months ago
- [NeurIPS 2021] Code for Learning Signal-Agnostic Manifolds of Neural Fields☆67Updated 2 years ago
- Video Autoencoder: self-supervised disentanglement of 3D structure and motion (ICCV 2021). Website: https://zlai0.github.io/VideoAutoenco…☆180Updated 3 years ago
- Code release for ICLR 2023 paper: SlotFormer on object-centric dynamics models☆106Updated last year