AI Paper Atlas

Research map / 3D vision / Gaussian splatting

iSplat: Iterative Learning for Fine-Grained Gaussian Splatting

Haifeng Wu, Wei Long, Shuhang Gu, Lixin Duan, Wen Li

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting

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 iterative GRU-based learning (3 passes) over single pass (ablation)iSplat · RealEstate10KPSNR: 26.95 -> 27.67Improved
add uncertainty-driven depth refinement instead of static range (ablation)iSplat · RealEstate10KPSNR: 27.10 -> 27.67Improved
add region-aware feature enhancement (ablation)iSplat · RealEstate10KPSNR: 27.42 -> 27.67Improved
increase iterations from 1 to 3 (train and test) (ablation)iSplat · RealEstate10KPSNR: 26.95 -> 27.60 -> 27.67Improved
increase iterations from 3 to 4 (ablation)iSplat · RealEstate10KPSNR: 27.67 -> 27.65No clear effect
mismatch training and test iteration counts (ablation)iSplat · RealEstate10KPSNR: 27.67 (3->3) vs 27.58 (3->1)Hurt
use iSplat (42.6M) instead of larger DepthSplat-L (354M)feed-forward 3DGS · RealEstate10KPSNR: 27.47 -> 27.67Improved
use iSplat instead of DepthSplat for zero-shot transferfeed-forward 3DGS · Re10k to DTUPSNR: 15.38 -> 18.26Improved
use iSplat instead of DepthSplat for zero-shot transferfeed-forward 3DGS · Re10k to ACIDPSNR: 28.37 -> 28.65Improved
add 3 iterative passes versus DepthSplat in inference costiSplat · RealEstate10Kinference time (s): 0.098 -> 0.124Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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