AI Paper Atlas

Research map / 3D vision / Gaussian splatting

BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting

Lingzhe Zhao, Peng Wang, Peidong Liu

ECCV 2024 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 71 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
increase number of virtual camera poses n from 3 to 10 (ablation)BAD-Gaussians · Tanabata (severe blur)PSNR: 25.43 -> 32.12Improved
increase n beyond 10 on a minor-blur scene (ablation)BAD-Gaussians · Cozy2roomPSNR: 34.68 -> 34.63 (n=10 to 20)No clear effect
use cubic B-spline instead of linear trajectory (ablation)BAD-Gaussians · Deblur-NeRF real scenesPSNR: 24.77 -> 26.11Improved
use cubic B-spline instead of linear trajectory (ablation)BAD-Gaussians · Deblur-NeRF syntheticPSNR: 33.92 -> 33.24Hurt
train Deblur-NeRF and DP-NeRF with ground-truth poses instead of COLMAP poses (ablation)DP-NeRF · Deblur-NeRF synthetic, CozyroomPSNR: 29.02 -> 30.77Improved
jointly optimize exposure-time camera trajectory with Gaussians using physical blur model, versus implicit BAD-NeRFBAD-Gaussians · Deblur-NeRF synthetic (deblurring)PSNR: 3.6 dB higher than second best on averageImproved
Gaussian representation versus NeRF for sky regionsBAD-Gaussians · Deblur-NeRF synthetic, FactoryPSNR: 31.88 vs 32.18 (BAD-NeRF)Hurt
plain 3D-GS or NeRF trained directly on blurred images3D-GS · Deblur-NeRF synthetic, TanabataPSNR: 20.51 vs 32.12 (BAD-Gaussians)Hurt

Later papers that compared with this method

2 later accepted papers report BAD-Gaussians* as a baseline in their results tables; 2 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 1 of 2 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