← Back to all news
arXiv Computer Vision By Yuhang Han, Hao Wang, Jiaxi Cao, Xingyu Liu

VGGT-GS SLAM: Uncalibrated Monocular Gaussian Splatting SLAM with Feed-Forward Priors

Read the original on arXiv Computer Vision →

VGGT-GS SLAM is a monocular 3D Gaussian Splatting SLAM system that operates on uncalibrated videos. It uses feed‑forward VGGT pose and depth priors to perform submap differentiable bundle adjustment, jointly refining camera poses, a 3D Gaussian map, and submap‑shared intrinsics and distortion parameters via analytic calibration Jacobians. The method introduces Gaussian‑native alignment for camera‑anchored scale refinement between submaps and loop‑closure verification, achieving improved localization accuracy and rendering quality on standard indoor benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 28

LingGS: Decoupling Feed-Forward Geometry Prediction from Camera Tracking for High-Fidelity Gaussian SLAM

The paper introduces LingGS, an online monocular RGB Gaussian splatting SLAM system that decouples feed‑forward geometry prediction from camera tracking. By leveraging a frozen streaming 3D foundation model as a virtual RGB‑D sensor for depth estimation and an explicit geometric solver for camera motion via feature reprojection, LingGS achieves higher tracking accuracy than learned predictions. Experiments on indoor and outdoor datasets demonstrate significant improvements in reconstruction quality, achieving about 7 FPS on a single RTX 4090 and 2–3× the throughput of prior SLAM systems.

By Da Li, Yihan Zang, Ivan Viola, Zeyu Wang, Dominik Engel
computer-visionefficiency
More like this →
arXiv Computer Vision
Aug 28

CGS-SLAM: Collaborative Gaussian Splatting based SLAM for Multi-Agent Reconstruction

CGS‑SLAM is a hybrid decentralized/centralized SLAM system that enables multi‑agent 3D Gaussian Splatting reconstruction using only RGB images and inertial data. Each agent locally tracks motion with inertial priors, builds a scaled map via a monocular depth estimator, and shares keyframe encodings to facilitate dynamic keyframing and submap alignment. A central server then aligns submaps with a view‑alignment model, keeping communication costs low while achieving competitive tracking, higher rendering quality, and accurate submap alignment in GNSS‑denied environments.

By Jean-Daniel de Ambrogi, Aladine Chetouani, Vincent Nguyen, Aur\'elien Chateigner
agentsbenchmarkssafety
More like this →
arXiv Computer Vision
6d ago

DrawSplat: Atlanta World-Guided Implicit Gaussian SLAM for Indoor Reconstruction

DrawSplat is an Atlanta World-guided implicit Gaussian SLAM framework designed for indoor reconstruction. It first sketches structural layout using explicit point-line geometry, then refines appearance and geometry with implicit neural Gaussians. The method jointly tracks camera poses, sparse geometry, and gravity, infers structural planes, and allocates Gaussian capacity to informative regions, achieving robust tracking, high-fidelity rendering, and strong geometric reconstruction while balancing quality, efficiency, and model size.

By Fan Zhu, Zhisong Xu, Ziyu Chen, Zhenjun Zhao, Takayuki Okatani
More like this →