AI Paper Atlas

Research map / 3D vision / Face and shape

Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction

Rui Peng, Shihe Shen, Kaiqiang Xiong, Huachen Gao, Jianbo Jiao, Xiaodong Gu, Ronggang Wang

ECCV 2024 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 3 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 end-to-end region sparsification (ablation)SuRF baseline · DTU ablationmean chamfer distance: 1.70 -> 1.02Improved
use multi-stage training instead of end-to-end sparsification (ablation)SuRF baseline · DTU ablationmean chamfer distance: 1.70 -> 1.52Improved
increase volume and image resolution (ablation)SuRF · DTU ablationmean chamfer distance: 1.12 -> 1.02Improved
increase number of scales from 1 to 4 (ablation)SuRF · DTU ablationmean chamfer distance: 1.38 -> 1.11Improved
increase number of scales from 4 to 5 (ablation)SuRF · DTU ablationmean chamfer distance: 1.11 -> 1.13Hurt
add cross-scale fusion (ablation)SuRF · DTU ablationmean chamfer distance: 1.15 -> 1.11Improved
add surface sampling (ablation)SuRF · DTU ablationmean chamfer distance: 1.13 -> 1.11Improved
add pseudo point cloud loss (beta 1.0) (ablation)SuRF · DTU ablationmean chamfer distance: 1.17 -> 1.11Improved
weight matching field loss increasing toward fine scales (ablation)SuRF · DTU ablationmean chamfer distance: 1.25 -> 1.11Improved
change surface region range ratios (ablation)SuRF · DTU ablationmean chamfer distance: 1.10 / 1.11 / 1.12No clear effect
learn surface region jointly with matching field instead of using RC-MVSNet region (ablation)SuRF · DTUmean chamfer distance: 1.13 -> 1.05Improved
use SuRF instead of C2F2NeuS in memory with more viewsC2F2NeuS · 9 input viewsmemory: 28G -> 3.1GImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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