AI Paper Atlas

Research map / 3D vision / Face and shape

Dual-S3D: Hierarchical Dual-Path Selective SSM-CNN for High-Fidelity Implicit Reconstruction

Luoxi Zhang, Pragyan Shrestha, Yu Zhou, Chun Xie, Itaru Kitahara

ICCV 2025 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 0 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
replace ViT Base with the selective SSM mixer encoder (ablation)Dual-S3D · Efficiency on RTX 3090FLOPs / inference time: 1,136.5 G -> 669.8 G FLOPs; 3.51 -> 1.52 sImproved
add auxiliary depth path to decouple geometry and RGB features (ablation)Dual-S3D · 3D-FRONTChamfer distance: 9.48 -> 6.60Improved
use multi-stage training (geometry first, then color) instead of single stage (ablation)Dual-S3D · 3D-FRONTChamfer distance: 9.91 -> 6.60Improved
add texture finetune stage with shallow RGB features (ablation)Dual-S3D · 3D-FRONT textureSSIM: 0.61 -> 0.83Improved
add texture finetune stage with shallow RGB features (ablation)Dual-S3D · 3D-FRONT geometryChamfer distance: 6.87 -> 6.60No clear effect
use Dual-S3D instead of SSR on 3D-FRONTsingle-view reconstruction · 3D-FRONTChamfer distance: 10.45 -> 6.60Improved
use Dual-S3D instead of SSR on Pix3Dsingle-view reconstruction · Pix3DChamfer distance: 21.79 -> 19.90Improved
train on 3D-FRONT and test on Pix3D (domain shift)Dual-S3D · Pix3DF-Score: 63.70 -> 49.43Hurt
Dual-S3D versus Zero-123 on texture LPIPSsingle-view reconstruction · 3D-FRONT textureLPIPS: Zero-123 0.12 vs Ours 0.14Hurt

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