AI Paper Atlas

Research map / 3D vision / Gaussian splatting

GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting

Wanshui Gan, Fang Liu, Hongbin Xu, Ningkai Mo, Naoto Yokoya

ICCV 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 39 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 mask-out strategy to Gaussian splatting scale-aware loss (ablation)GaussianOcc stage 1 · nuScenes depthAbs Rel: 0.798 -> 0.293Improved
add erosion of the binary overlap mask (ablation)GaussianOcc stage 1 · nuScenes depthAbs Rel: 0.293 -> 0.281Improved
add depth refinement with fixed pose net (ablation)GaussianOcc stage 1 · nuScenes depthAbs Rel: 0.281 -> 0.258Improved
use two-stage training instead of one stage (ablation)GaussianOcc · nuScenes depthAbs Rel: 0.946 -> 0.211Improved
use learned pose instead of GT pose (ablation)GaussianOcc stage 2 · nuScenes depthAbs Rel: 0.214 -> 0.211No clear effect
use learned pose instead of prior-work learned pose (ablation)GaussianOcc stage 2 · nuScenes depthAbs Rel: 0.235 -> 0.211Improved
use learnable Gaussian scale instead of fixed 0.1 (ablation)splatting rendering · nuScenes depthAbs Rel: 0.217 -> 0.212Improved
use splatting rendering instead of volume rendering with GT pose (ablation)GaussianOcc · nuScenes occupancymIoU*: 10.81 -> 11.30Improved
use splatting rendering instead of volume rendering with learned pose (ablation)GaussianOcc · nuScenes occupancyAbs Rel: 0.506 -> 0.197Improved
use splatting rendering with small scale 0.05 (ablation)splatting rendering · nuScenes depthAbs Rel: 0.215 -> 0.223Hurt
use splatting instead of volume rendering for render timeGaussianOcc · nuScenes occupancyrender time per 180x320 (s): 0.85 -> 0.17Improved
use splatting instead of volume rendering for training timeGaussianOcc · nuScenes occupancytraining time per epoch (h): 2.68 -> 1Improved

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