EgoM2P: Egocentric Multimodal Multitask Pretraining

• URL: http://arxiv.org/abs/2506.07886v1
• Date: Mon, 09 Jun 2025 15:59:25 GMT
• Title: EgoM2P: Egocentric Multimodal Multitask Pretraining
• Authors: Gen Li, Yutong Chen, Yiqian Wu, Kaifeng Zhao, Marc Pollefeys, Siyu Tang,
• Abstract summary: Building large-scale egocentric multimodal and multitask models presents unique challenges.<n> EgoM2P is a masked modeling framework that learns from temporally aware multimodal tokens to train a large, general-purpose model for egocentric 4D understanding.<n>We will fully open-source EgoM2P to support the community and advance egocentric vision research.
• Score: 55.259234688003545
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding multimodal signals in egocentric vision, such as RGB video, depth, camera poses, and gaze, is essential for applications in augmented reality, robotics, and human-computer interaction. These capabilities enable systems to better interpret the camera wearer's actions, intentions, and surrounding environment. However, building large-scale egocentric multimodal and multitask models presents unique challenges. Egocentric data are inherently heterogeneous, with large variations in modality coverage across devices and settings. Generating pseudo-labels for missing modalities, such as gaze or head-mounted camera trajectories, is often infeasible, making standard supervised learning approaches difficult to scale. Furthermore, dynamic camera motion and the complex temporal and spatial structure of first-person video pose additional challenges for the direct application of existing multimodal foundation models. To address these challenges, we introduce a set of efficient temporal tokenizers and propose EgoM2P, a masked modeling framework that learns from temporally aware multimodal tokens to train a large, general-purpose model for egocentric 4D understanding. This unified design supports multitasking across diverse egocentric perception and synthesis tasks, including gaze prediction, egocentric camera tracking, and monocular depth estimation from egocentric video. EgoM2P also serves as a generative model for conditional egocentric video synthesis. Across these tasks, EgoM2P matches or outperforms specialist models while being an order of magnitude faster. We will fully open-source EgoM2P to support the community and advance egocentric vision research. Project page: https://egom2p.github.io/

Related papers

• PlayerOne: Egocentric World Simulator [73.88786358213694]
  PlayerOne is the first egocentric realistic world simulator.<n>It generates egocentric videos that are strictly aligned with the real scene human motion of the user captured by an exocentric camera.
  arXiv  Detail & Related papers  (2025-06-11T17:59:53Z)
• GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control [122.65089441381741]
  We present GEM, a Generalizable Ego-vision Multimodal world model.<n>It predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories.<n>Our dataset is comprised of 4000+ hours of multimodal data across domains like autonomous driving, egocentric human activities, and drone flights.
  arXiv  Detail & Related papers  (2024-12-15T14:21:19Z)
• Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos [25.41337525728398]
  EgoMono4D is a novel model that unifies the estimation of multiple variables necessary for Egocentric Monocular 4D reconstruction.<n>It achieves superior performance in dense pointclouds sequence reconstruction compared to all baselines.
  arXiv  Detail & Related papers  (2024-11-14T02:57:11Z)
• MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA [72.47344411599322]
  This research aims to explore building a multimodal foundation model for egocentric video understanding.<n>We automatically generate 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long in Ego4D based on human-annotated data.<n>We contribute a challenging egocentric QA benchmark with 629 videos and 7,026 questions to evaluate the models' ability in recognizing and memorizing visual details across videos of varying lengths.
  arXiv  Detail & Related papers  (2024-10-09T17:59:59Z)
• EgoLM: Multi-Modal Language Model of Egocentric Motions [42.36945117610459]
  We present EgoLM, a versatile framework that tracks and understands egocentric motions from multi-modal inputs. Our key insight is to model the joint distribution of egocentric motions and natural languages using large language models.
  arXiv  Detail & Related papers  (2024-09-26T17:59:31Z)
• EgoGen: An Egocentric Synthetic Data Generator [53.32942235801499]
  EgoGen is a new synthetic data generator that can produce accurate and rich ground-truth training data for egocentric perception tasks. At the heart of EgoGen is a novel human motion synthesis model that directly leverages egocentric visual inputs of a virtual human to sense the 3D environment. We demonstrate EgoGen's efficacy in three tasks: mapping and localization for head-mounted cameras, egocentric camera tracking, and human mesh recovery from egocentric views.
  arXiv  Detail & Related papers  (2024-01-16T18:55:22Z)
• 3D Human Pose Perception from Egocentric Stereo Videos [67.9563319914377]
  We propose a new transformer-based framework to improve egocentric stereo 3D human pose estimation. Our method is able to accurately estimate human poses even in challenging scenarios, such as crouching and sitting. We will release UnrealEgo2, UnrealEgo-RW, and trained models on our project page.
  arXiv  Detail & Related papers  (2023-12-30T21:21:54Z)
• Ego-Body Pose Estimation via Ego-Head Pose Estimation [22.08240141115053]
  Estimating 3D human motion from an egocentric video sequence plays a critical role in human behavior understanding and has various applications in VR/AR. We propose a new method, Ego-Body Pose Estimation via Ego-Head Pose Estimation (EgoEgo), which decomposes the problem into two stages, connected by the head motion as an intermediate representation. This disentanglement of head and body pose eliminates the need for training datasets with paired egocentric videos and 3D human motion.
  arXiv  Detail & Related papers  (2022-12-09T02:25:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.