AI Paper Atlas

Research map / 3D vision / Gaussian splatting

BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modeling

Cheng Peng, Yutao Tang, Yifan Zhou, Nengyu Wang, Xijun Liu, Deming Li, Rama Chellappa

ECCV 2024 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 38 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 Blur Proposal Network with coarse-to-fine kernel optimization to Mip-SplattingMip-Splatting · Deblur-NeRF camera motion blurPSNR: 21.87 -> 26.70Improved
add BAGS to Mip-Splatting on defocus blurMip-Splatting · Deblur-NeRF defocus blurPSNR: 21.08 -> 23.95Improved
add BAGS on mixed-resolution unbounded scenesMip-Splatting · Mip-NeRF 360 mixed resolutionPSNR: 26.11 -> 27.11Improved
add BAGS on low-light drone motion blurMip-Splatting · Low-light dronePSNR: 26.50 -> 29.86Improved
pre-restore images with HAT super-resolution before Mip-SplattingMip-Splatting · Mip-NeRF 360 mixed resolutionPSNR: 26.11 -> 24.99Hurt
pre-restore images with MPR deblurring before Mip-SplattingMip-Splatting · Low-light dronePSNR: 26.50 -> 26.36No clear effect
add RGBD features to the Blur Proposal Network (ablation)BAGS · camera motion and defocus blurPSNR: +1.57/0.92 dB PSNR, +0.03/0.03 SSIMImproved
add coarse-to-fine kernel optimization (ablation)BAGS · defocus blurPSNR: +1.64 dB PSNR, +0.08 SSIMImproved
use dense full kernel instead of sparse deformable kernel (ablation)BAGS · camera motion blurPSNR/SSIMImproved
increase final kernel size K1 (ablation)BAGS · motion/defocus and low-light scenariosreconstruction qualityImproved
increase final kernel size K1 (ablation)BAGS · mixed resolutionreconstruction qualityHurt
use coarse-to-fine training instead of single-scale training (ablation)BAGS · training timetraining time: under fifteen minutes vs two hours for PDRFImproved

Later papers that compared with this method

6 later accepted papers report BAGS as a baseline in their results tables; 5 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 4 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