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.
arXiv:2603.12064v3 Announce Type: replace Abstract: We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a settin...
TAPVid-MV is a new benchmark for tracking any point in 3D across multiple synchronized camera views. It comprises 284 sequences, 1,142 calibrated camera streams, and 109,769 point tracks, covering indoor and outdoor domains and derived from various modalities such as depth, LiDAR, SLAM, and simulation. The dataset is visually verified, and evaluation shows that current multi‑view trackers do not consistently outperform monocular trackers, highlighting geometry recovery as a key bottleneck.
Anchor3R is a streaming 3D reconstruction framework that predicts window-relative poses and local geometry in the current‑frame coordinate system, forming a dense relative‑pose graph for online pose updates and loop‑aware motion averaging. It improves long‑horizon pose accuracy and dense reconstruction quality on indoor, outdoor, driving, and RGB‑D benchmarks, and generalizes from 48‑frame training sequences to streams exceeding 10,000 frames while keeping GPU memory bounded. The method addresses issues of train‑test mismatch, early‑anchor bias, and accumulated drift found in previous streaming models.
LonGaussian is a streaming feed‑forward framework that reconstructs compact, globally renderable Gaussian scenes from long image sequences with known intrinsics and unknown camera poses. It decodes long‑context geometric features into dense Gaussians, links repeated observations via multi‑frame point tracks, and consolidates predictions with a learned merger. Rendered‑depth consistency filtering removes incorrectly occluding Gaussians, leading to improved novel‑view rendering quality on DL3DV and RealEstate10K benchmarks while using fewer Gaussians than baseline methods.
arXiv:2608.29003v1 Announce Type: cross Abstract: In dynamic and unstructured environments, conventional SLAM systems generally suffer from significant accuracy degeneration due to their static assum...
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.
The paper introduces 3DROID, a dataset of renderable 3D Gaussian scenes that are anchored to a robot’s metric workspace and include per-scene reliability metrics. It examines how the reliability of camera extrinsics and pose conditioning affect the fidelity of 3D Gaussian representations, proposing a calibration-aware pipeline that improves novel-view rendering when extrinsics are trustworthy. The resulting dataset, available on Hugging Face, provides robot manipulation researchers with metric-scale, pose-anchored 3D data and reliability annotations.
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.
arXiv:2609.25746v1 Announce Type: cross Abstract: ICP-based 3D Gaussian Splatting (3DGS) SLAM tracks in real time by registering incoming frames against map Gaussians, using each primitive's covarian...
arXiv:2607.24495v2 Announce Type: replace Abstract: Structured-light (SL) cameras power depth sensing in millions of devices, and recent neural SL decoding methods have substantially improved their d...
arXiv:2610.01314v1 Announce Type: new Abstract: Dynamic scenes may be captured by a moving camera, multiple video streams, or images taken at different times. These observations reveal complementary...
arXiv:2609.17387v1 Announce Type: new Abstract: Real-time dense SLAM is a core capability for robotics applications that require robust localization and high- quality mapping in dynamic or fast-chang...