Paper

GFreeDet: Exploiting Gaussian Splatting and Foundation Models for Model-free Unseen Object Detection in the BOP Challenge 2024

Xingyu Liu

Yingyue Li

Chengxi Li

Gu Wang

Chenyangguang Zhang

Ziqin Huang

Xiangyang Ji

In this report, we provide the technical details of the submitted method GFreeDet, which exploits Gaussian splatting and vision Foundation models for the model-free unseen object Detection track in the BOP 2024 Challenge.

PDF URL

Featured

News

Japan's Infrastructure Ministry Registers a 3D Gaussian Splatting Method in NETIS

Japan's MLIT registers a 3D Gaussian Splatting method from Tohoku University and XMAT in NETIS, building bridge and tunnel models from 360-degree camera images.

Michael Rubloff

Oct 7, 2026

Platforms

Nicolas Diolez Releases Mask Bridge to Export AI Masks and Lightroom Selections From Lightroom Classic

Mask Bridge is a Lightroom Classic plugin that exports RF-DETR AI masks, estimated silhouettes of Lightroom masks and transparent cutouts with matching names.

Michael Rubloff

Oct 7, 2026

Platforms

SplatGen Trains and Relights Gaussian Splats Inside the Blender 5.3 Alpha

SplatGen's preview for the Blender 5.3 Alpha builds camera datasets, trains Gaussian splats with a new V2 trainer, and relights them in EEVEE and Cycles.

Michael Rubloff

Oct 7, 2026

Platforms

Spirula Studio v2026.10.6 Brings Laser Scans Into Its Training Pipeline

Spirula Studio v2026.10.6 adds experimental E57, LAS and PLY laser scan support for metric scale and depth and normal maps, plus a region of interest editor.

Michael Rubloff

Oct 6, 2026