2 stories · covering 11/14 6:30 – 11/17 6:30 (JST)

This issue covers two arXiv papers: one on SLAM calibration and relocalization, and one on removing disturbances in 4D reconstruction.

  1. 01 GEMOR-GS: A 3DGS SLAM Method with LiDAR-Camera Calibration and Online Relocalization Appears on arXiv Research arxiv.org
  2. 02 ReCan-GS: A 4D Gaussian Reconstruction Method That Removes Distractors Without Masks (arXiv) Research arxiv.org

Issue 2026.11.17 Research 2 stories / Next issue: 11/20(Fri)7:00

In this issue

01Research

GEMOR-GS: A 3DGS SLAM Method with LiDAR-Camera Calibration and Online Relocalization Appears on arXiv

Yuchen Yang and colleagues have released GEMOR-GS, a 3DGS mapping method for LiDAR-inertial-visual SLAM. It combines prior estimation of extrinsic calibration, global reconstruction, and relocalization after tracking loss.

Why it mattersOn the other hand, the method assumes a procedure in which a calibration segment is captured beforehand. For field use, the effort this requires and the conditions for fixing the equipment need to be estimated.

Source: arxiv.orgRead more

02Research

ReCan-GS: A 4D Gaussian Reconstruction Method That Removes Distractors Without Masks (arXiv)

Joel Julin and colleagues have posted ReCan-GS to arXiv. It separates occluders, shadows, and smoke or fog from 4D reconstructions of dynamic scenes. According to the paper, it uses a sensitivity score from the deformation field to tell valid motion apart from distractors.

Why it mattersWhen dynamic scenes are reconstructed from everyday video or handheld footage, intrusions such as passersby, shadows, and smoke can lower quality. If distractors can be separated without relying on mask creation or segmentation models, the method could reduce the preprocessing effort for 4D material. However, its practical effectiveness needs to be checked against a released implementation and quantitative results.

Source: arxiv.orgRead more

Get it by email

We send the latest issue every 3 days at 7:00 JST (in Japanese).

The newsletter is sent in Japanese only. You can subscribe on the Japanese page.