SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.18771 · CVPR · 2024

NARUTO: Neural Active Reconstruction from Uncertain Target Observations

Yi Xu, Zheng Chen, Bing Li, Xiangyu Xu, Qingan Yan, Ziyue Feng, Changjiang Cai, Huangying Zhan, Qilun Zhu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present NARUTO, a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning, enabling high-fidelity surface reconstruction. Our approach leverages a multi-resolution hashgrid as the mapping backbone, chosen for its exceptional convergence speed and capacity to capture high-frequency local features. The centerpiece of our work is the incorporation of an uncertainty learning module that dynamically quantifies reconstruction uncertainty while actively reconstructing the environment. By harnessing learned uncertainty, we propose a novel uncertainty aggregation strategy for goal searching and efficient path planning. Our system autonomously explores by targeting uncertain observations and reconstructs environments with remarkable completeness and fidelity. We also demonstrate the utility of this uncertainty-aware approach by enhancing SOTA neural SLAM systems through an active ray sampling strategy. Extensive evaluations of NARUTO in various environments, using an indoor scene simulator, confirm its superior performance and state-of-the-art status in active reconstruction, as evidenced by its impressive results on benchmark datasets like Replica and MP3D. Project page: oppo-usresearch.github.io/NARUTO-website/

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.18771")
get_code_for_paper("2402.18771")
have("2402.18771")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.18771.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.18771.svg)](https://syntology.ai/paper/2402.18771)

Connect an agent — have() is free.