AI Paper Atlas

Research map / 3D vision / Depth and stereo

PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction

Jiahui Ren, Mochu Xiang, Jiajun Zhu, Yuchao Dai

ICCV 2025 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 7 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
use unposed PanoSplatt3R instead of posed panorama methodsPanoSplatt3R · HM3DPSNR: Splatter-360 28.308 -> 28.938Improved
use PanoSplatt3R instead of Splatter-360 on SSIMPanoSplatt3R · HM3DSSIM: 0.875 -> 0.869Hurt
feed posed methods with SIFT+8PA estimated posesSplatter-360 · HM3DPSNR: 28.308 -> 14.765Hurt
initialize from MASt3R perspective pretrained weights instead of random (ablation)PanoSplatt3R · HM3DPSNR: 23.331 -> 28.200Improved
add RoPE rolling (ablation)PanoSplatt3R · HM3DPSNR: 27.916 -> 28.200Improved
use RoPE rolling instead of setting max rotation angle to 2pi (ablation)PanoSplatt3R · HM3DPSNR: 26.849 -> 28.200Improved
add two-stage progressive training (centers first) (ablation)PanoSplatt3R · HM3DPSNR: 27.217 -> 28.200Improved
use 2DGS instead of 3DGS (ablation)PanoSplatt3R · HM3DPSNR: 28.049 -> 28.200Improved
apply uniform scale recovery to the reconstruction (ablation)PanoSplatt3R · ReplicaPSNR: 28.181 -> 31.522Improved
compare to fixed-baseline PanSplat at narrow baseline (1.0m)PanoSplatt3R · Matterport3D (1.0m)WS-PSNR: 30.01 -> 27.47Hurt
compare to fixed-baseline PanSplat at wider baseline (2.0m)PanoSplatt3R · Matterport3D (2.0m)WS-PSNR: 21.19 -> 23.65Improved

Later papers that compared with this method

1 later accepted paper reports PanoSplatt3R 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 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