AI Paper Atlas

Research map / 3D vision / Gaussian splatting

ARTDECO: Toward High-Fidelity On-the-Fly Reconstruction with Hierarchical Gaussian Structure and Feed-Forward Guidance

Guanghao Li, Kerui Ren, Linning Xu, Zhewen Zheng, Changjian Jiang, Xin Gao, Bo Dai, Jian Pu, Mulin Yu, Jiangmiao Pang

ICLR 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views

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 level-of-detail Gaussians (ablation)ARTDECO · ScanNet++ renderingPSNR: 28.13 -> 29.12Improved
add implicit structural Gaussians (ablation)ARTDECO · ScanNet++ renderingPSNR: 28.54 -> 29.12Improved
add global features (ablation)ARTDECO · ScanNet++ renderingPSNR: 28.89 -> 29.12Improved
add mapper frames (ablation)ARTDECO · ScanNet++ renderingPSNR: 26.38 -> 29.12Improved
add common frames (ablation)ARTDECO · ScanNet++ renderingPSNR: 27.20 -> 29.12Improved
add mapper frames (ablation)ARTDECO · ScanNet++ renderingLPIPS: 0.229 -> 0.167Improved
add loop closure (ablation)ARTDECO · ScanNet++ trackingATE RMSE: 0.057 -> 0.018Improved
use MASt3R instead of pi3 as feed-forward backbone (ablation)ARTDECO · ScanNet++ trackingATE RMSE: 0.374 -> 0.018Improved
use pi3 instead of VGGT in loop module (ablation)ARTDECO · ScanNet++ trackingATE RMSE: 0.096 -> 0.018Hurt
track with both mapper frames and keyframes (dense) (ablation)ARTDECO · ScanNet++ trackingATE RMSE: 0.018 -> 0.094Hurt
ARTDECO vs LongSplat on training timeARTDECO · ScanNet++training time: 442.96 min -> 5.33 minImproved
ARTDECO vs MASt3R-SLAM trackingARTDECO · ScanNet++ATE RMSE: 0.025 -> 0.018Improved

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