從自動編輯的 3D Gaussian Splatting 中學習,以進行線上貝葉斯場景變化檢測
Learning from Automatic 3D Gaussian Splatting Edits for Online Bayesian Scene Change Detection
該方法從自動編輯的 3D Gaussian Splatting 表徵中學習場景專屬證據模型及先驗,透過貝葉斯融合和物件引導細化進行線上場景變化檢測。在 PASLCD 和 CCS3D 上,方法分別取得 67.64% 和 75.82% mIoU,達到最先進準確度。在 PASLCD 上,完整流程處理完整查詢序列的速度為 17.2 FPS,為受評估線上方法中最快。
Published on Oct 21
Authors:
Abstract
The method learns scene-specific evidence models and priors from automatically edited 3D Gaussian Splatting representations to perform efficient online change detection via Bayesian fusion and object-guided refinement.
Online scene change detection requires integrating incoming observations to determine which regions have changed relative to a reference scene. We update change beliefs as new images arrive using generalised Bayesian evidence fusion. However, the prior probability of change and evidence models are unknown beforehand, and numerical Bayesian inference can be costly. We address these challenges by learning offline from automatic edits to a reference 3D Gaussian Splatting (3DGS) model. These edits generate labelled training views without manual annotations. Together with unchanged reference observations, they provide supervision for learning scene-specific evidence models and estimating the effective pixel prior and response statistics. Online prediction combines current evidence with historical support, while closed-form local Bayes factors, parameterized by the learned response statistics, update an accumulated 3D Gaussian field. Object-guided refinement produces the final change masks. Our method achieves state-of-the-art accuracy on PASLCD and CCS3D, with 67.64% and 75.82% mIoU, respectively. On PASLCD, the complete pipeline runs at 17.2\,FPS over complete query sequences, the fastest among the evaluated online methods. Project page: https://changruizhu96.github.io/work/lego-scd/
View arXiv page View PDF Project page GitHub Add to collection
Models citing this paper 1
Updated 24 minutes agoTeleeeeeeeeeee/LEGO-SCD
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.28490 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.28490 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co