AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion

Zihan Wang, Jeff Tan, Tarasha Khurana, Neehar Peri, Deva Ramanan

ICCV 2025 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 10 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 space-time consistent depth initialization (DUSt3R-aligned MoGe) (ablation)MonoFusion baseline · held-out views ablationPSNR: 26.19 -> 29.55Improved
add feature-metric loss L_feat (ablation)MonoFusion baseline · held-out views ablationPSNR / IoU: PSNR 26.19 -> 25.39; IoU 0.60 -> 0.63Mixed
add feature-metric loss on top of our depth (ablation)MonoFusion · held-out views ablationPSNR / IoU: PSNR 29.55 -> 29.31; IoU 0.73 -> 0.75Mixed
add feature-clustering motion bases (ablation)MonoFusion · held-out views ablationPSNR: 29.31 -> 30.40Improved
use feature-based instead of velocity-based motion bases (ablation)MonoFusion · 4-camera sparse viewqualitativeImproved
use fewer than 20 motion bases (ablation)MonoFusion · sparse-view reconstructionqualitativeHurt
increase motion bases beyond 28 (ablation)MonoFusion · sparse-view reconstructionqualitativeNo clear effect
use globally-consistent DUSt3R depth only (MV-SOM-DS) instead of DUSt3R+MoGe alignment (ablation)MV-SOM · ExoReconPSNR: 30.43 -> 28.37Hurt
improve metric depth estimator in MV-SOM (UniDepthV2) (ablation)MV-SOM · ExoReconPSNR: 26.91 -> 27.65 (still below MonoFusion 30.64)Improved
MonoFusion vs monocular Shape of Motion on held-out viewsMonoFusion · Panoptic StudioPSNR: 17.86 -> 28.01Improved

Later papers that compared with this method

2 later accepted papers report MonoFusion* as a baseline in their results tables; 2 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 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