AI Paper Atlas

Research map / 3D vision / Gaussian splatting

FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction

Jiale Xu, Shenghua Gao, Ying Shan

ICCV 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 33 citations (OpenAlex)

Read the paper

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 pixel-alignment loss (ablation)FreeSplatter-O · GSOPSNR: 26.684 -> 30.443Improved
add pixel-alignment loss (ablation)FreeSplatter-S · ScanNet++PSNR: 21.330 -> 25.807Improved
add pixel-alignment loss (ablation)FreeSplatter-S · ScanNet++LPIPS: 0.201 -> 0.140Improved
increase layers from 16 to 24 at patch size 8 (ablation)FreeSplatter-O · GSOPSNR: 28.945 -> 30.443Improved
increase layers from 16 to 24 at patch size 16 (ablation)FreeSplatter-O · GSOPSNR: 25.417 -> 28.622Improved
reduce patch size from 16 to 8 at 24 layers (ablation)FreeSplatter-O · GSOPSNR: 28.622 -> 30.443Improved
reduce patch size from 16 to 8 at 16 layers (ablation)FreeSplatter-O · GSOPSNR: 25.417 -> 28.945Improved
pose-free FreeSplatter-O versus pose-dependent LGM using GT posesFreeSplatter-O · GSOPSNR: 24.463 -> 30.443Improved
pose-free FreeSplatter-O versus pose-dependent InstantMesh using GT posesFreeSplatter-O · OmniObject3DPSNR: 24.077 -> 31.929Improved
FreeSplatter-O versus PF-LRM on PF-LRM's GSO eval data (GT novel-view poses)FreeSplatter-O · GSO (PF-LRM eval data)PSNR: 25.08 -> 23.54Hurt
FreeSplatter-O versus PF-LRM on PF-LRM's OmniObject3D eval dataFreeSplatter-O · OmniObject3D (PF-LRM eval data)PSNR: 21.77 -> 22.83Improved
end-to-end FreeSplatter-S versus Splatt3R with frozen MASt3RFreeSplatter-S · ScanNet++PSNR: 21.013 -> 25.807Improved

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