Saved in:
Bibliographic Details
Main Authors: Xu, Xiaohao, Xue, Feng, Zhao, Shibo, Pan, Yike, Scherer, Sebastian, Huang, Xiaonan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.09723
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912154035159040
author Xu, Xiaohao
Xue, Feng
Zhao, Shibo
Pan, Yike
Scherer, Sebastian
Huang, Xiaonan
author_facet Xu, Xiaohao
Xue, Feng
Zhao, Shibo
Pan, Yike
Scherer, Sebastian
Huang, Xiaonan
contents Real-time multi-agent collaboration for ego-motion estimation and high-fidelity 3D reconstruction is vital for scalable spatial intelligence. However, traditional methods produce sparse, low-detail maps, while recent dense mapping approaches struggle with high latency. To overcome these challenges, we present MAC-Ego3D, a novel framework for real-time collaborative photorealistic 3D reconstruction via Multi-Agent Gaussian Consensus. MAC-Ego3D enables agents to independently construct, align, and iteratively refine local maps using a unified Gaussian splat representation. Through Intra-Agent Gaussian Consensus, it enforces spatial coherence among neighboring Gaussian splats within an agent. For global alignment, parallelized Inter-Agent Gaussian Consensus, which asynchronously aligns and optimizes local maps by regularizing multi-agent Gaussian splats, seamlessly integrates them into a high-fidelity 3D model. Leveraging Gaussian primitives, MAC-Ego3D supports efficient RGB-D rendering, enabling rapid inter-agent Gaussian association and alignment. MAC-Ego3D bridges local precision and global coherence, delivering higher efficiency, largely reducing localization error, and improving mapping fidelity. It establishes a new SOTA on synthetic and real-world benchmarks, achieving a 15x increase in inference speed, order-of-magnitude reductions in ego-motion estimation error for partial cases, and RGB PSNR gains of 4 to 10 dB. Our code will be made publicly available at https://github.com/Xiaohao-Xu/MAC-Ego3D .
format Preprint
id arxiv_https___arxiv_org_abs_2412_09723
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D Reconstruction
Xu, Xiaohao
Xue, Feng
Zhao, Shibo
Pan, Yike
Scherer, Sebastian
Huang, Xiaonan
Computer Vision and Pattern Recognition
Real-time multi-agent collaboration for ego-motion estimation and high-fidelity 3D reconstruction is vital for scalable spatial intelligence. However, traditional methods produce sparse, low-detail maps, while recent dense mapping approaches struggle with high latency. To overcome these challenges, we present MAC-Ego3D, a novel framework for real-time collaborative photorealistic 3D reconstruction via Multi-Agent Gaussian Consensus. MAC-Ego3D enables agents to independently construct, align, and iteratively refine local maps using a unified Gaussian splat representation. Through Intra-Agent Gaussian Consensus, it enforces spatial coherence among neighboring Gaussian splats within an agent. For global alignment, parallelized Inter-Agent Gaussian Consensus, which asynchronously aligns and optimizes local maps by regularizing multi-agent Gaussian splats, seamlessly integrates them into a high-fidelity 3D model. Leveraging Gaussian primitives, MAC-Ego3D supports efficient RGB-D rendering, enabling rapid inter-agent Gaussian association and alignment. MAC-Ego3D bridges local precision and global coherence, delivering higher efficiency, largely reducing localization error, and improving mapping fidelity. It establishes a new SOTA on synthetic and real-world benchmarks, achieving a 15x increase in inference speed, order-of-magnitude reductions in ego-motion estimation error for partial cases, and RGB PSNR gains of 4 to 10 dB. Our code will be made publicly available at https://github.com/Xiaohao-Xu/MAC-Ego3D .
title MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.09723