paper-with-me

Papers

EgoPet: Egomotion and Interaction Data from an Animal's Perspective

2024-04-15 · Amir Bar, Arya Bakhtiar, Danny Tran, Antonio Loquercio, Jathushan Rajasegaran, Yann Lecun, Amir Globerson, Trevor Darrell

Animals perceive the world to plan their actions and interact with other agents to accomplish complex tasks, demonstrating capabilities that are still unmatched by AI systems. To advance our understanding and reduce the gap between the capabilities of animals and AI systems, we introduce a dataset of pet egomotion imagery with diverse examples of simultaneous egomotion and multi-agent interaction. Current video datasets separately contain egomotion and interaction examples, but rarely both at the same time. In addition, EgoPet offers a radically distinct perspective from existing egocentric datasets of humans or vehicles. We define two in-domain benchmark tasks that capture animal behavior, and a third benchmark to assess the utility of EgoPet as a pretraining resource to robotic quadruped locomotion, showing that models trained from EgoPet outperform those trained from prior datasets.

📄 PDF Abstract BibTeX arXiv:2404.09991

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LegoPET: Hierarchical Feature Guided Conditional Diffusion for PET Image Reconstruction

2024-11-25 · Yiran Sun, Osama Mawlawi

Positron emission tomography (PET) is widely utilized for cancer detection due to its ability to visualize functional and biological processes in vivo. PET images are usually reconstructed from histogrammed raw data (sin…

Image ReconstructionSSIM

EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent

2025-07-21 · Jiaao Li, Kaiyuan Li, Chen Gao, Yong Li 외

Egomotion videos are first-person recordings where the view changes continuously due to the agent's movement. As they serve as the primary visual input for embodied AI agents, making egomotion video reasoning more effici…

Multimodal Reasoning

Fast, Robust, Continuous Monocular Egomotion Computation

2016-02-16 · Andrew Jaegle, Stephen Phillips, Kostas Daniilidis

We propose robust methods for estimating camera egomotion in noisy, real-world monocular image sequences in the general case of unknown observer rotation and translation with two views and a small baseline. This is a dif…

counterfactualMotion EstimationOptical Flow EstimationTranslation

UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation

2025-08-02 · Chaitanya Patel, Hiroki Nakamura, Yuta Kyuragi, Kazuki Kozuka 외 arxiv

Egocentric human motion generation and forecasting with scene-context is crucial for enhancing AR/VR experiences, improving human-robot interaction, advancing assistive technologies, and enabling adaptive healthcare solu…

Motion ForecastingMotion Synthesis

On the Coupling of Depth and Egomotion Networks for Self-Supervised Structure from Motion

2021-06-07 · Brandon Wagstaff, Valentin Peretroukhin, Jonathan Kelly

Structure from motion (SfM) has recently been formulated as a self-supervised learning problem, where neural network models of depth and egomotion are learned jointly through view synthesis. Herein, we address the open p…

Self-Supervised Learning