allenai / objathorLinks
Python package for importing and loading external assets into AI2THOR
☆25Updated 2 months ago
Alternatives and similar repositories for objathor
Users that are interested in objathor are comparing it to the libraries listed below
Sorting:
- Dreamitate: Real-World Visuomotor Policy Learning via Video Generation (CoRL 2024)☆50Updated 2 months ago
- ☆16Updated last year
- main augmentation script for real world robot dataset.☆35Updated 2 years ago
- ☆61Updated 2 years ago
- Code for Ditto in the House: Building Articulation Models of Indoor Scenes through Interactive Perception☆17Updated 2 years ago
- Official PyTorch implementation of Doduo: Dense Visual Correspondence from Unsupervised Semantic-Aware Flow☆44Updated last year
- Code Repository for "Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations"☆60Updated 8 months ago
- [ICCV 2023] Understanding 3D Object Interaction from a Single Image☆46Updated last year
- [ICRA 2024] Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Models☆69Updated last year
- IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos☆49Updated 5 months ago
- (Incomplete version) This is an implementation of affordancellm.☆13Updated 10 months ago
- Code for "Steerable Scene Generation with Post Training and Inference-Time Search", CORL 2025☆45Updated 3 months ago
- Scaling up Robot Learning in Simulation with Generative Models☆48Updated last year
- Code repository for the Habitat Synthetic Scenes Dataset (HSSD) paper.☆101Updated last year
- Official Implementation of ARM4R ICML 2025☆44Updated last month
- ☆78Updated 3 months ago
- Language-based navigation project☆22Updated last year
- Teaching robots to respond to open-vocab queries with CLIP and NeRF-like neural fields☆174Updated last year
- ☆107Updated 5 months ago
- [CoRL 2022] This repository contains code for generating relevancies, training, and evaluating Semantic Abstraction.☆114Updated 2 years ago
- Code for the RSS 2023 paper "Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement"☆20Updated 2 years ago
- ☆35Updated last month
- code for the paper Predicting Point Tracks from Internet Videos enables Diverse Zero-Shot Manipulation☆93Updated last year
- Code for "SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields" (ECCV 2024)☆12Updated 10 months ago
- GUI for intuitively creating 3D reconstructions of the real world☆26Updated last year
- [CoRL 2025] UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations☆59Updated last week
- [ECCV 2022, Oral] OPD: Single-view 3D Openable Part Detection☆33Updated 2 years ago
- [CoRL 2023] Rearrangement Planning for General Part Assembly☆26Updated 11 months ago
- The ProcTHOR-10K Houses Dataset☆109Updated 2 years ago
- [ECCV'24] Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer☆74Updated last year