AI Paper Atlas

Research map / 3D vision / Depth and stereo

ManifoldNeuS: Manifold-aware View Optimizability for Pose-Free Neural Surface Reconstruction

Xinxin Liu, Xue Wang, Guoqing Zhou, Qing Wang

CVPR 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction

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 MaVOS-based view scheduling to naive NeuS-BARF (ablation)NeuS-BARF · DTU Scan24rotation error (deg): 168.05 -> 36.02Improved
add MaVOS-gated positional encoding (ablation)ManifoldNeuS · DTU Scan24rotation error (deg): 1.80 -> 0.80Improved
add anti-score loss weighting instead of base weighting (ablation)ManifoldNeuS · DTU Scan24rotation error (deg): 2.09 -> 0.80Improved
add manifold coverage term to MaVOS (ablation)ManifoldNeuS · DTU Scan24rotation error (deg): 1.38 -> 0.80Improved
add dynamic refinement (reordering successors) to view scheduling (ablation)ManifoldNeuS · DTU Scan24rotation error (deg): 4.07 -> 0.80Improved
use ManifoldNeuS instead of VGGT for pose estimationpose-free reconstruction · DTU (9 scenes) averagerotation error (deg): 2.300 -> 0.602Improved
use ManifoldNeuS instead of VGGT for pose estimation on Scan24pose-free reconstruction · DTU Scan24rotation error (deg): 0.516 -> 0.795Hurt
use ManifoldNeuS identity-initialized instead of NeuS-BARFpose-free NeuS · DTU (9 scenes) averagerotation error (deg): 118.475 -> 0.602Improved
use ManifoldNeuS pose-free instead of NeuS with COLMAP posessurface reconstruction · DTU (9 scenes) averageChamfer distance: 0.368 -> 0.404Hurt
use ManifoldNeuS instead of SG-NeRF for reconstructionsurface reconstruction · DTU (9 scenes) averageChamfer distance: 0.590 -> 0.404Improved

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