AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views

Wangze Xu, Huachen Gao, Shihe Shen, Rui Peng, Jianbo Jiao, Ronggang Wang

ECCV 2024 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 31 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
add forward-warping appearance constraint (L_fwd) for unseen views (ablation)MVPGS · LLFF 3-view (res 8x)PSNR: 17.32 -> 20.39Improved
add consistent structure regularization L_CS (ablation)MVPGS · LLFF 3-view (res 8x)PSNR: 20.06 -> 20.39Improved
add monocular depth rank loss L_mono (ablation)MVPGS · LLFF 3-view (res 8x)PSNR: 20.17 -> 20.39Improved
initialize 3DGS with MVS point clouds instead of COLMAP points (ablation)3DGS · LLFF 3-view (res 8x)PSNR: 14.87 -> 16.16Improved
replace COLMAP init with MVS init alone, without other components3DGS · LLFF 3-viewPSNR: 14.87 -> 16.16Mixed
swap MVS pretraining data (DTU, BlendedMVS, DTU+BlendedMVS ft) (ablation)MVPGS · LLFF 3-view (res 8x)PSNR: 20.39 / 20.17 / 20.34No clear effect
apply MVPGS versus FreeNeRF/SparseNeRF on T&T large-scale scenesMVPGS · T&T 3-viewPSNR: 20.62 -> 25.57Improved
use MVPGS in 2-view extremely sparse settingMVPGS · LLFF 2-view (res 8x)PSNR: 17.44 -> 18.53Improved
increase to 5 input views on LLFFMVPGS · LLFF 5-view (res 8x)PSNR: 22.18 vs FreeNeRF 22.57Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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