cs.RONov 9, 2026

DPGS-SLAM: Diffusion-Prior and Provenance-Aware Monocular Gaussian Splatting SLAM for Dynamic Visual Sensing

Authors: Yifan Luo, Takafumi Matsumaru, Vibekananda Dutta, Xin He

Organizations: Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Fukuoka 808-0135, Japan · Faculty of Mechatronics, Warsaw University of Technology, 00-661 Warsaw, Poland · School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Abstract

This paper presents DPGS-SLAM (Diffusion-Prior and Provenance-Aware Monocular Gaussian Splatting SLAM) for dense mapping in environments containing dynamic objects. Objects in dynamic motion remain a significant challenge for dense visual SLAM since dynamic observations can contaminate camera tracking and scene reconstruction. Although 3DGS (3D Gaussian splatting) enables efficient dense mapping, existing 3DGS-SLAM systems may exhibit instability when dynamic objects violate their underlying static-scene assumption. Excluding dynamic observations can reduce their influence on tracking and mapping, but may leave occluded static backgrounds missing or weakly constrained. Our proposed DPGS-SLAM is a monocular RGB SLAM framework that supports provisional representations of insufficiently observed static backgrounds through asynchronous diffusion-based background completion and provenance-aware Gaussian mapping. Dynamic regions are identified through optical-flow-based motion discovery and temporally consistent mask propagation by SAM2. For selected keyframes, a fine-tuned diffusion inpainting model generates plausible background appearance in occluded regions, while metric depth predicted from completed images initializes provisional Gaussian primitives. Provenance labels distinguish generated primitives from observation-supported primitives, excluding generated content from camera-pose estimation and observed-map optimization. When previously occluded backgrounds become visible, eligible generated primitives are removed, and observation-supported primitives are independently initialized from real RGB observations and predicted depth. Experimental results demonstrated competitive camera tracking, with average ATE RMSE values of 1.2 cm on TUM RGB-D and 2.7 cm on BONN RGB-D datasets. On StaDy4D, DPGS-SLAM improved average PSNR by 4.60 dB over WildGS-SLAM using only monocular RGB input.

Figures & tables

Explore similar work

CardsList
  1. RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos

    Aug 29, 2026Wenting Wang, Jiaxin Guo, Wenzhen Dong +3Dynamic SLAMVisual SLAM

  2. GGD-SLAM: Monocular 3DGS SLAM Powered by Generalizable Motion Model for Dynamic Environments

    Apr 14, 2026Yi Liu, Haoxuan Xu, Hongbo Duan +5Dynamic SLAM3DGS SLAM