AI Paper Atlas

Research map / 3D vision / Gaussian splatting

FlowR: Flowing from Sparse to Dense 3D Reconstructions

Tobias Fischer, Samuel Rota Bulò, Yung-Hsu Yang, Nikhil Keetha, Lorenzo Porzi, Norman Müller, Katja Schwarz, Jonathon Luiten, Marc Pollefeys, Peter Kontschieder

ICCV 2025 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 14 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 rendering-conditioned source distribution p0(z|y) instead of Gaussian noise (ablation)FlowR flow matching · DL3DV140SSIM: 0.769 -> 0.808Improved
use rendering-conditioned source distribution instead of Gaussian noise (ablation)FlowR flow matching · ScanNet++PSNR: 24.09 -> 25.53Improved
use rendering-conditioned source distribution instead of Gaussian noise (ablation)FlowR flow matching · DL3DV140LPIPS: 0.200 -> 0.180Improved
add alternative target-view loss L_tgt (L2, SSIM, LPIPS) instead of vanilla L_GS (ablation)FlowR refined reconstruction · DL3DV140LPIPS: 0.279 -> 0.248Improved
add re-initialization of pointcloud with generated views (ablation)FlowR refined reconstruction · DL3DV140PSNR: 23.72 -> 23.78Improved
add re-initialization with generated views in 24-view split (ablation)FlowR refined reconstruction · DL3DV140 (24-view)PSNR: 25.10 -> 25.13Improved
add MASt3R dense pointcloud initialization instead of Splatfacto default (ablation)initial reconstruction · DL3DV140PSNR: 19.44 -> 21.72Improved
add co-visibility graph G_vis (ablation)initial reconstruction · DL3DV140view pairs: 342 -> 129Improved
add re-triangulation of matches (ablation)initial reconstruction · DL3DV140PSNR: 21.76 -> 22.23; LPIPS 0.293 -> 0.322Mixed
add adaptive density control with 5K steps (ablation)initial reconstruction · DL3DV140LPIPS: 0.322 -> 0.292Improved
train longer (30K instead of 5K steps) (ablation)initial reconstruction · DL3DV140PSNR: 22.58 -> 22.21No clear effect
add flow refinement of test views (FlowR++) on top of FlowR (ablation)FlowR · ScanNet++LPIPS: 0.303 -> 0.250Improved

Later papers that compared with this method

1 later accepted paper reports FlowR 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 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