AI Paper Atlas

Research map / 3D vision / Gaussian splatting

IRIS: Intersection-aware Ray-based Implicit Editable Scenes

Grzegorz Wilczyński, Mikołaj Zieliński, Krzysztof Byrski, Joanna Waczynska, Dominik Belter, Przemysław Spurek

ECCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 1 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 max intersections per ray from 16 to 128 (ablation)IRIS · NeRF Synthetic ablation (avg)PSNR: 29.87 -> 32.65Improved
increase max intersections per ray from 64 to 128 (ablation)IRIS · NeRF Synthetic ablation (avg)PSNR: 32.47 -> 32.65Improved
add multi-resolution hash grid feature initialization (ablation)IRIS · NeRF Synthetic ablation (avg)PSNR: 32.54 -> 32.65Improved
use analytical ray-intersection sampling instead of EKS grid samplingIRIS · NeRF Synthetic (average)FPS: 0.183 -> 6.038Improved
use IRIS instead of EKS for trainingIRIS · NeRF Synthetic (average)training time: 26h 2min -> 51min 18sImproved
use IRIS instead of EKSIRIS · NeRF Synthetic (average)PSNR: 33.12 -> 32.65Hurt
use IRIS instead of EKS on outdoor scenesIRIS · Mip-NeRF 360 outdoorPSNR: 20.70 -> 24.11Improved
use IRIS instead of Radiance Meshes on outdoor scenesIRIS · Mip-NeRF 360 outdoorPSNR: 24.73 -> 24.11Hurt
use IRIS instead of Radiance Meshes on indoor scenesIRIS · Mip-NeRF 360 indoorPSNR: 29.29 -> 30.85Improved
use IRIS instead of EKS on deformation benchmarkIRIS · NeuralEditor deformation benchmark (avg)PSNR: 25.92 -> 25.70No clear effect
use IRIS instead of NeuralEditor on deformation benchmarkIRIS · NeuralEditor deformation benchmark (avg)PSNR: 25.12 -> 25.70Improved
use ray intersection selector instead of proposal or volumetric sampler at large batchIRIS · Sampler throughputscalabilityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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