Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Shijie, Ren, Hui, Weng, Yijia, Zhang, Shuwang, Wang, Zhen, Xu, Dejia, Fan, Zhiwen, You, Suya, Wang, Zhangyang, Guibas, Leonidas, Kadambi, Achuta
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910897253908480
author Zhou, Shijie
Ren, Hui
Weng, Yijia
Zhang, Shuwang
Wang, Zhen
Xu, Dejia
Fan, Zhiwen
You, Suya
Wang, Zhangyang
Guibas, Leonidas
Kadambi, Achuta
author_facet Zhou, Shijie
Ren, Hui
Weng, Yijia
Zhang, Shuwang
Wang, Zhen
Xu, Dejia
Fan, Zhiwen
You, Suya
Wang, Zhangyang
Guibas, Leonidas
Kadambi, Achuta
contents Recent advancements in 2D and multimodal models have achieved remarkable success by leveraging large-scale training on extensive datasets. However, extending these achievements to enable free-form interactions and high-level semantic operations with complex 3D/4D scenes remains challenging. This difficulty stems from the limited availability of large-scale, annotated 3D/4D or multi-view datasets, which are crucial for generalizable vision and language tasks such as open-vocabulary and prompt-based segmentation, language-guided editing, and visual question answering (VQA). In this paper, we introduce Feature4X, a universal framework designed to extend any functionality from 2D vision foundation model into the 4D realm, using only monocular video input, which is widely available from user-generated content. The "X" in Feature4X represents its versatility, enabling any task through adaptable, model-conditioned 4D feature field distillation. At the core of our framework is a dynamic optimization strategy that unifies multiple model capabilities into a single representation. Additionally, to the best of our knowledge, Feature4X is the first method to distill and lift the features of video foundation models (e.g., SAM2, InternVideo2) into an explicit 4D feature field using Gaussian Splatting. Our experiments showcase novel view segment anything, geometric and appearance scene editing, and free-form VQA across all time steps, empowered by LLMs in feedback loops. These advancements broaden the scope of agentic AI applications by providing a foundation for scalable, contextually and spatiotemporally aware systems capable of immersive dynamic 4D scene interaction.
format Preprint
id arxiv_https___arxiv_org_abs_2503_20776
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
Zhou, Shijie
Ren, Hui
Weng, Yijia
Zhang, Shuwang
Wang, Zhen
Xu, Dejia
Fan, Zhiwen
You, Suya
Wang, Zhangyang
Guibas, Leonidas
Kadambi, Achuta
Computer Vision and Pattern Recognition
Recent advancements in 2D and multimodal models have achieved remarkable success by leveraging large-scale training on extensive datasets. However, extending these achievements to enable free-form interactions and high-level semantic operations with complex 3D/4D scenes remains challenging. This difficulty stems from the limited availability of large-scale, annotated 3D/4D or multi-view datasets, which are crucial for generalizable vision and language tasks such as open-vocabulary and prompt-based segmentation, language-guided editing, and visual question answering (VQA). In this paper, we introduce Feature4X, a universal framework designed to extend any functionality from 2D vision foundation model into the 4D realm, using only monocular video input, which is widely available from user-generated content. The "X" in Feature4X represents its versatility, enabling any task through adaptable, model-conditioned 4D feature field distillation. At the core of our framework is a dynamic optimization strategy that unifies multiple model capabilities into a single representation. Additionally, to the best of our knowledge, Feature4X is the first method to distill and lift the features of video foundation models (e.g., SAM2, InternVideo2) into an explicit 4D feature field using Gaussian Splatting. Our experiments showcase novel view segment anything, geometric and appearance scene editing, and free-form VQA across all time steps, empowered by LLMs in feedback loops. These advancements broaden the scope of agentic AI applications by providing a foundation for scalable, contextually and spatiotemporally aware systems capable of immersive dynamic 4D scene interaction.
title Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.20776