EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos

• URL: http://arxiv.org/abs/2504.11732v1
• Date: Wed, 16 Apr 2025 03:12:39 GMT
• Title: EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos
• Authors: Jilan Xu, Yifei Huang, Baoqi Pei, Junlin Hou, Qingqiu Li, Guo Chen, Yuejie Zhang, Rui Feng, Weidi Xie,
• Abstract summary: Given an exo-centric video, the first frame of the corresponding ego-centric video, and textual instructions, the goal is to generate futur frames of the ego-centric video.<n>EgoExo-Gen explicitly models the hand-object dynamics for cross-view video prediction.
• Score: 49.24266108952835
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating videos in the first-person perspective has broad application prospects in the field of augmented reality and embodied intelligence. In this work, we explore the cross-view video prediction task, where given an exo-centric video, the first frame of the corresponding ego-centric video, and textual instructions, the goal is to generate futur frames of the ego-centric video. Inspired by the notion that hand-object interactions (HOI) in ego-centric videos represent the primary intentions and actions of the current actor, we present EgoExo-Gen that explicitly models the hand-object dynamics for cross-view video prediction. EgoExo-Gen consists of two stages. First, we design a cross-view HOI mask prediction model that anticipates the HOI masks in future ego-frames by modeling the spatio-temporal ego-exo correspondence. Next, we employ a video diffusion model to predict future ego-frames using the first ego-frame and textual instructions, while incorporating the HOI masks as structural guidance to enhance prediction quality. To facilitate training, we develop an automated pipeline to generate pseudo HOI masks for both ego- and exo-videos by exploiting vision foundation models. Extensive experiments demonstrate that our proposed EgoExo-Gen achieves better prediction performance compared to previous video prediction models on the Ego-Exo4D and H2O benchmark datasets, with the HOI masks significantly improving the generation of hands and interactive objects in the ego-centric videos.

Related papers

• Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations [47.04855334955006]
  We propose a novel masked ego-exo modeling that promotes both causal temporal dynamics and cross-view alignment.<n>We highlight the importance of capturing the compositional nature of human actions as a basis for robust cross-view understanding.
  arXiv  Detail & Related papers  (2025-03-25T14:33:32Z)
• Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding [69.96199605596138]
  Current MLLMs primarily focus on third-person (exocentric) vision, overlooking the unique aspects of first-person (egocentric) videos. We propose learning the mapping between exocentric and egocentric domains to enhance egocentric video understanding. We introduce Ego-ExoClip, a pre-training dataset comprising 1.1M synchronized ego-exo clip-text pairs.
  arXiv  Detail & Related papers  (2025-03-12T08:10:33Z)
• EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation [54.32133648259802]
  We present our solutions to the EgoVis Challenges in CVPR 2024, including five tracks in the Ego4D challenge and three tracks in the EPIC-Kitchens challenge. Building upon the video-language two-tower model and leveraging our meticulously organized egocentric video data, we introduce a novel foundation model called EgoVideo. This model is specifically designed to cater to the unique characteristics of egocentric videos and provides strong support for our competition submissions.
  arXiv  Detail & Related papers  (2024-06-26T05:01:37Z)
• Object Aware Egocentric Online Action Detection [23.504280692701272]
  We introduce an Object-Aware Module that integrates egocentric-specific priors into existing Online Action Detection frameworks. Our work can be seamlessly integrated into existing models with minimal overhead and bring consistent performance enhancements.
  arXiv  Detail & Related papers  (2024-06-03T07:58:40Z)
• EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videos [9.340890244344497]
  Existing methods for forecasting 2D hand positions rely on visual representations and mainly focus on hand-object interactions. We propose EMAG, an ego-motion-aware and generalizable 2D hand forecasting method. Our model outperforms prior methods by 1.7% and 7.0% on intra and cross-dataset evaluations.
  arXiv  Detail & Related papers  (2024-05-30T13:15:18Z)
• Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions? [48.702973928321946]
  Egocentric video-language pretraining is a crucial step in advancing the understanding of hand-object interactions in first-person scenarios.<n>Despite successes on existing testbeds, we find that current EgoVLMs can be easily misled by simple modifications.<n>This raises the question: Do EgoVLMs truly understand hand-object interactions?
  arXiv  Detail & Related papers  (2024-05-28T00:27:29Z)
• Retrieval-Augmented Egocentric Video Captioning [53.2951243928289]
  EgoInstructor is a retrieval-augmented multimodal captioning model that automatically retrieves semantically relevant third-person instructional videos. We train the cross-view retrieval module with a novel EgoExoNCE loss that pulls egocentric and exocentric video features closer by aligning them to shared text features that describe similar actions.
  arXiv  Detail & Related papers  (2024-01-01T15:31:06Z)
• Egocentric Video-Language Pretraining [74.04740069230692]
  Video-Language Pretraining aims to learn transferable representation to advance a wide range of video-text downstream tasks. We exploit the recently released Ego4D dataset to pioneer Egocentric training along three directions. We demonstrate strong performance on five egocentric downstream tasks across three datasets.
  arXiv  Detail & Related papers  (2022-06-03T16:28:58Z)
• Generative Adversarial Network for Future Hand Segmentation from Egocentric Video [25.308139917320673]
  We introduce the novel problem of anticipating a time series of future hand masks from ego video. A key challenge is to model thetemporality of future head motions, which globally impact the head-worn camera video analysis.
  arXiv  Detail & Related papers  (2022-03-21T19:41:44Z)

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.