AI Paper Atlas

Research map / 3D vision / Face and shape

GaINeR: Geometry-Aware Implicit Neural Representation for Image Editing

Weronika Jakubowska, Mikołaj Zieliński, Rafał Tobiasz, Krzysztof Byrski, Maciej Zieba, Dominik Belter, Przemysław Spurek

ECCV 2026 · 3D vision › Face and shape · approach: Implicit neural representation design · 0 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
replace MiraGe with GaINeRGaussian-based image representation · Kodak reconstructionPSNR: 59.52 -> 77.09Improved
replace MiraGe with GaINeRGaussian-based image representation · DIV2K reconstructionPSNR: 54.54 to 62.20Improved
replace MiraGe with GaINeR under identical 500k fixed GaussiansGaussian-based image representation · Kodak (identical setup)PSNR: 62.49 -> 77.09Improved
replace MiraGe with GaINeR under identical 500k fixed GaussiansGaussian-based image representation · DIV2K (identical setup)PSNR: 58.45 -> 62.20Improved
use GaINeR instead of GaussianImageGaussian-based image representation · Kodak (identical setup)PSNR: 30.46 -> 77.09Improved
replace MiraGe with GaINeR for MS-SSIMGaussian-based image representation · Kodak reconstructionMS-SSIM: 0.9999 -> 0.9999No clear effect
replace MiraGe with GaINeR in physics-based editingPhysics-based deformation · Physics-based editingMUSIQ: 61.03 -> 62.62Improved
replace MiraGe with GaINeR in physics-based editingPhysics-based deformation · Physics-based editingFID: 372.41 -> 376.34Hurt
use GaINeR instead of explicit point cloud reprojection with GT depthSingle-image NVS · Hotdog NVS (GT depth)PSNR: 8.57 -> 20.58Improved
use GaINeR instead of explicit point cloud reprojection with GT depthSingle-image NVS · Scan 114 DTU NVS (GT depth)PSNR: 13.51 -> 18.09Improved
use Depth-Pro estimated depth instead of ground-truth depthGaINeR single-image NVS · Hotdog NVSPSNR: 20.58 -> 19.50Hurt
use Depth-Pro estimated depth instead of ground-truth depthGaINeR single-image NVS · Scan 114 DTU NVSPSNR: 18.09 -> 17.74Hurt

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