mihirp1998 / Disentangling-3D-Prototypical-Nets
We present neural architectures that disentangle RGB-D images into objects' shapes and styles and a map of the background scene, and explore their applications for few-shot 3D object detection and few-shot concept classification.
☆11Updated 3 years ago
Related projects: ⓘ
- Official Release of ICLR 2020 paper "SCALOR: Generative World Models with Scalable Object Representations"☆48Updated 8 months ago
- [ICML 2022] Official PyTorch implementation of the paper "Unsupervised Image Representation Learning with Deep Latent Particles"☆24Updated 11 months ago
- Neural Networks that convert input movies into Physical Scene Graphs (PSGs)☆61Updated 3 years ago
- SNARE Dataset with MATCH and LaGOR models☆23Updated 5 months ago
- [ICML 2020] Visual Grounding of Learned Physical Models☆37Updated 3 years ago
- Official Code for Neural Systematic Binder☆28Updated last year
- Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation (ECCV 2020)☆31Updated 10 months ago
- ☆24Updated 3 months ago
- Code for "Learning Affordance Landscapes for Interaction Exploration in 3D Environments" (NeurIPS 20)☆34Updated last year
- Learning Long-term Visual Dynamics with Region Proposal Interaction Networks (ICLR 2021)☆112Updated 2 years ago
- Unsupervised learning of Object Landmarks through Conditional Image Generation☆46Updated 4 years ago
- Official code for Slot-Transformer for Videos (STEVE)☆41Updated last year
- Pytorch implementation of "Move to See Better: Self-Improving Embodied Object Detection" (https://arxiv.org/abs/2012.00057)☆23Updated 3 years ago
- Video Autoencoder: self-supervised disentanglement of 3D structure and motion (ICCV 2021). Website: https://zlai0.github.io/VideoAutoenco…☆176Updated 2 years ago
- Evaluating pre-trained navigation agents under corruptions☆27Updated 3 years ago
- Official PyTorch implementation of "Improving Generative Imagination in Object-Centric World Models"☆34Updated last year
- Code, data and benchmark from the paper "Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences".☆36Updated 3 years ago
- This paper contains code for our work "An Exploration of Embodied Visual Exploration".☆62Updated 3 years ago
- ☆39Updated 7 months ago
- "CoPhy: Counterfactual Learning of Physical Dynamics", F. Baradel, N. Neverova, J. Mille, G. Mori, C. Wolf, ICLR'2020☆33Updated 4 years ago
- Learning low-shot object classification with explicit shape bias learned from point clouds☆43Updated 2 years ago
- ☆59Updated 2 years ago
- Task planning over 3D scene graphs☆16Updated 2 years ago
- [TMLR 2024] Official PyTorch Implementation of Deep Dynamic Latent Particles☆14Updated 7 months ago
- ☆25Updated 2 years ago
- Learning about objects and their properties by interacting with them☆12Updated 3 years ago
- Official implementation of: "Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions" by Villar-Corrales et al…☆14Updated 11 months ago
- [NeurIPS 2021] Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language☆45Updated last year
- Official PyTorch implementation of 'RELATE: Physically Plausible Multi-Object SceneSynthesis Using Structured Latent Spaces'.☆32Updated 3 years ago
- ☆148Updated last year