AI Paper Atlas

Research map / 3D vision / Gaussian splatting

VEGS: View Extrapolation of Urban Scenes in 3D Gaussian Splatting using Learned Priors

Sungwon Hwang, Min-Jung Kim, Taewoong Kang, Jayeon Kang, Jaegul Choo

ECCV 2024 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 16 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 VEGS priors (normal and diffusion) and dynamic modeling to 3DGS for extrapolated views3DGS · KITTI-360 EVSFID: 211.8 -> 124.4Improved
add surface-normal covariance guidance to LiDAR-initialized 3DGS+ (ablation)3DGS+ · KITTI-360 EVSFID: 126.3 -> 124.6Improved
add diffusion score distillation prior on top of normal prior (ablation)VEGS · KITTI-360 EVSFID: 124.6 -> 124.4Improved
add L_axis covariance axes loss (ablation)VEGS · KITTI-360 EVS-DFID: 123.28 -> 122.56Improved
add both L_axis and L_scale (ablation)VEGS · KITTI-360 EVS-DFID: 123.28 -> 121.60Improved
optimize VEGS vs MARS on conventional test camerasVEGS · KITTI-360 test camerasSSIM: 0.814 (MARS) vs 0.812No clear effect
use VEGS vs 3DGS+ on conventional test cameras3DGS+ · KITTI-360 test camerasPSNR: 23.76 -> 23.71No clear effect
add dynamic scene modeling, LiDAR init and box optimization to 3DGS (ablation)3DGS · KITTI-360FID: 211.8 -> 126.3Improved
add VEGS priors on KITTI3DGS+ · KITTI EVSKID: 0.207 -> 0.090Improved
evaluate on extrapolated views versus conventional test camerasMARS · KITTI-360FID: PSNR 23.13 on test cams vs FID 131.1 on EVSMixed

Later papers that compared with this method

1 later accepted paper reports VEGS as a baseline in their results tables; 1 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 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