most citedCompact 3D Gaussian Splatting For Dense Visual SLAM

7 citations · 7 across the 2 of their papers we have counts for

collaborators

8 papers

cs.RO2026

Does Robust VIO Need More Learning? Geometry-Verified Visual Measurements under Distribution Shift

Yangyang Ning, Shu Liang, Quanbo Ge +3

Learning is increasingly introduced into visual-inertial odometry (VIO), ranging from learned feature front-ends to learning-dominant motion and geometry estimation. However, learn…

cs.CV20267 cited

Compact 3D Gaussian Splatting For Dense Visual SLAM

Tianchen Deng, Chang Nie, Shuhong Liu +6

Recent work has shown that 3D Gaussian-based SLAM enables high-quality reconstruction, accurate pose estimation, and real-time rendering of scenes. However, these approaches are bu…

cs.RO2026

What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models

Tianchen Deng, Yue Pan, Shenghai Yuan +10

In this paper, we provide a comprehensive overview of existing scene representation methods for robotics, covering traditional representations such as point clouds, voxels, signed…

cs.CV2026

VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenes

Tianchen Deng, Wenhua Wu, Junjie He +4

3D Gaussian Splatting has recently shown promising results in dense visual SLAM. However, existing 3DGS-based SLAM methods are all constrained to small-room scenarios and struggle…

cs.CV2026

ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarios

Yihan Wei, Shenghai Yuan, Tianchen Deng +2

Corner cases are rare or extreme scenarios that drive real-world failures, but they are difficult to curate at scale: web data are noisy, labels are brittle, and edge deployments p…

cs.CV2025

Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer

Tianchen Deng, Wenhua Wu, Kunzhen Wu +7

Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a lat…