Skip to search formSkip to main contentSkip to account menu

AI2-THOR: An Interactive 3D Environment for Visual AI

AI2-THOR consists of near photo-realistic 3D indoor scenes, where AI agents can navigate in the scenes and interact with objects to perform tasks and facilitate building visually intelligent models.
View PDF on arXiv (opens in a new tab)

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

A self-adaptive visual navigation method (SAVN) which learns to adapt to new environments without any explicit supervision which shows major improvements in both success rate and SPL for visual navigation in novel scenes.
View on IEEE (opens in a new tab)

Watching the World Go By: Representation Learning from Unlabeled Videos

Video Noise Contrastive Estimation is proposed, a method for using unlabeled video to learn strong, transferable single image representations that demonstrate improvements over recent unsupervised single image techniques, as well as over fully supervised ImageNet pretraining, across a variety of temporal and non-temporal tasks.
View PDF on arXiv (opens in a new tab)

SeGAN: Segmenting and Generating the Invisible

This paper studies the challenging problem of completing the appearance of occluded objects and proposes a novel solution, SeGAN, which outperforms state-of-the-art segmentation baselines for the invisible parts of objects.
View on IEEE (opens in a new tab)

Contrasting Contrastive Self-Supervised Representation Learning Pipelines

This paper analyzes contrastive approaches as one of the most successful and popular variants of self-supervised representation learning and examines over 700 training experiments including 30 encoders, 4 pre-training datasets and 20 diverse downstream tasks.
View on IEEE (opens in a new tab)

Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects

This paper addresses the problem of inferring contact points and the physical forces from videos of humans interacting with objects by using a physics simulator to predict effects, and enforce that estimated forces must lead to same effect as depicted in the video.
View on IEEE (opens in a new tab)

ManipulaTHOR: A Framework for Visual Object Manipulation

This work proposes a framework for object manipulation built upon the physics-enabled, visually rich AI2-THOR framework and presents a new challenge to the Embodied AI community known as ArmPointNav, which extends the popular point navigation task to object manipulation and offers new challenges including 3D obstacle avoidance.
View on IEEE (opens in a new tab)

ProcTHOR: Large-Scale Embodied AI Using Procedural Generation

The proposed PROCTHOR, a framework for procedural generation of Embodied AI environments, enables us to sample arbitrarily large datasets of diverse, interactive, customizable, and performant virtual environments to train and evaluate embodied agents across navigation, interaction, and manipulation tasks.
View PDF on arXiv (opens in a new tab)

Continuous Scene Representations for Embodied AI

Using CSR, state-of-the-art approaches for the challenging downstream task of visual room rearrangement are outperformed, without any task specific training and the learned embeddings capture salient spatial details of the scene and show applicability to real world data.
View on IEEE (opens in a new tab)

Contrasting Contrastive Self-Supervised Representation Learning Models

This paper analyzes contrastive approaches as one of the most successful and popular variants of self-supervised representation learning and examines over 700 training experiments including 30 encoders, 4 pre-training datasets and 20 diverse downstream tasks.
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)