AI Paper Atlas

Research map / 3D vision / 3D generation

GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

Yuanhui Huang, Wenzhao Zheng, Yunpeng Zhang, Jie Zhou, Jiwen Lu

ECCV 2024 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction · 108 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
use 3D Gaussian representation instead of dense grids for occupancyGaussianFormer · nuScenes efficiencymemory (M): 26500 M (OctreeOcc) -> 6229 MImproved
GaussianFormer vs best dense method on accuracyGaussianFormer · nuScenes valSSC mIoU: 20.30 -> 19.10Hurt
GaussianFormer vs planar representation BEVFormerGaussianFormer · nuScenes valSSC mIoU: 16.75 -> 19.10Improved
GaussianFormer on monocular KITTI-360 vs SymphoniesGaussianFormer · SSCBench-KITTI-360 valSSC mIoU: 18.58 -> 12.92Hurt
add 3D sparse convolution self-encoding (ablation)GaussianFormer · nuScenes val (51200 Gaussians)mIoU: 15.93 -> 16.41Improved
add deep supervision on each refinement module (ablation)GaussianFormer · nuScenes val (51200 Gaussians)mIoU: 16.36 -> 16.41Improved
refine properties by direct substitution instead of residual mean refinement (ablation)GaussianFormer · nuScenes val (51200 Gaussians)mIoU: collapses (no result)Hurt
apply residual refinement to all properties except semantics (ablation)GaussianFormer · nuScenes val (51200 Gaussians)mIoU: 16.41 -> 16.24Hurt
increase number of Gaussians from 25600 to 144000 (ablation)GaussianFormer · nuScenes valmIoU: 16.00 -> 19.10Improved
add photometric reconstruction loss (ablation)GaussianFormer · nuScenes val (51200 Gaussians)mIoU: 16.41 -> 16.24No clear effect
add split and prune strategy from offline 3D-GS (ablation)GaussianFormer · nuScenes val (51200 Gaussians)mIoU: 16.41 -> 16.50No clear effect
initialize Gaussians from predicted pseudo point cloud instead of learnable (ablation)GaussianFormer · nuScenes val (51200 Gaussians)mIoU: 16.41 -> 18.99Improved

Later papers that compared with this method

8 later accepted papers report GaussianFormer as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 4 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