AI Paper Atlas

Research map / 3D vision / Gaussian splatting

GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting

Baijun Ye, Minghui Qin, Saining Zhang, Moonjun Gong, Shaoting Zhu, Hao Zhao, Hang Zhao

ICCV 2025 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add octree-based Gaussian surfel with ground Gaussians over GVKFGS-Occ3D · Waymo Static-32Chamfer Distance: 0.82 -> 0.56Improved
use 5 cameras instead of 3 as input (ablation)GS-Occ3D · Waymo Static-32CD-Pcd: 0.66 -> 0.56Improved
use 5 cameras instead of 3 as input (ablation)GVKF · Waymo Static-32CD-Pcd: 0.87 -> 0.82Hurt
use 5 cameras instead of 3 as input (ablation)PGSR · Waymo Static-32CD-Pcd: 2.90 -> 3.63Hurt
use 5 cameras instead of 3 as input (ablation)2DGS · Waymo Static-32CD-Pcd: 1.23 -> 1.25No clear effect
use point cloud directly instead of converting Gaussians to mesh (ablation)GVKF · Waymo Static-32 (5Cam)Chamfer Distance: 1.22 -> 0.82Improved
add separate ground Gaussians (ablation)GS-based reconstruction · Waymo Static-32geometry (qualitative)Improved
train occupancy model on vision-only labels instead of Occ3D LiDAR labels, evaluate zero-shot on nuScenesCVT-Occ · Occ3D-nuScenes valIoU: 31.4 -> 33.4Improved
train occupancy model on vision-only labels instead of Occ3D LiDAR labels, evaluate on Occ3D-Waymo valCVT-Occ · Occ3D-Val WaymoIoU: 57.4 -> 44.7Hurt
train occupancy model on vision-only labels instead of Occ3D labels, evaluate on Ours-ValCVT-Occ · Ours-Val WaymoIoU: 41.1 -> 46.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy