AI Paper Atlas

Research map / 3D vision / Face and shape

SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies

Liang Han, Xu Zhang, Haichuan Song, Kanle Shi, Yu-Shen Liu, Zhizhong Han

ICCV 2025 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 6 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 volume rendering-based feature consistency loss (ablation)NeuS with color loss · DTU (3 small-overlapping views)Chamfer Distance: 1.76 -> 1.47Improved
add uncertainty-guided depth constraint (ablation)NeuS with color loss · DTU (3 small-overlapping views)Chamfer Distance: 1.76 -> 1.62Improved
combine feature consistency and depth constraint (ablation)NeuS with color loss · DTU (3 small-overlapping views)Chamfer Distance: 1.47 -> 1.11Improved
add color consistency loss (warping) to NeuS baseline (ablation)NeuS · DTU (3 small-overlapping views)Chamfer Distance: 3.35 -> 1.76Improved
use uncertainty-guided depth loss with COLMAP calibration instead of MonoSDF-style depth loss (ablation)SparseRecon · DTU (3 small-overlapping views)Chamfer Distance: 1.59 -> 1.11Improved
use cosine feature similarity instead of L1 distance (ablation)volume-rendering feature consistency · DTU (3 small-overlapping views)Chamfer Distance: 2.36 -> 1.11Improved
use cosine feature similarity instead of L2 distance (ablation)volume-rendering feature consistency · DTU (3 small-overlapping views)Chamfer Distance: 1.81 -> 1.11Improved
compute feature consistency over all points along ray (volume rendering) instead of on-surface point only (ablation)SparseRecon · DTU (3 small-overlapping views)Chamfer Distance: 2.93 -> 1.11Improved
SparseRecon vs best prior overfitting/generalization methodSparseRecon · DTU (3 small-overlapping views)mean Chamfer Distance: 1.39 -> 1.11Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 7 of 7 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