AI Paper Atlas

Research map / 3D vision / Face and shape

Learning 3D Shape Fidelity Metric from Real-world Distortions

Xuelu Feng, Tianyu Luan, Zixin Zhu, Akshobhya Sharma, Phani Nuney, Junsong Yuan, Chunming Qiao

CVPR 2026 · 3D vision › Face and shape · approach: Optimization-based shape matching

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 LoRA-style finetuning of the pretrained PointNet MLPs (ablation)LoCaSE · RSF main (train/test split)PLCC: 0.671 -> 0.728Improved
add local attention within vertex mesh neighborhoods (ablation)LoCaSE · RSF main (train/test split)PLCC: 0.605 -> 0.728Improved
use both local attention and LoRA (ablation)LoCaSE · RSF main (train/test split)PLCC: 0.597 -> 0.728Improved
use mesh-topology local attention instead of ball query (ablation)LoCaSE · RSF main (train/test split)PLCC: 0.645 -> 0.728Improved
train on real-distortion RSF data instead of synthetic ShapeGrading only (ablation)LoCaSE · RSF main (train/test split)PLCC: 0.380 -> 0.728Improved
use ModelNet-pretrained PointNet plus LoRA instead of training from scratch (ablation)LoCaSE · RSF main (train/test split)PLCC: 0.697 -> 0.728Improved
replace simple PointNet backbone with MeshCNN, DiffusionNet, PointNet++ or DGCNN (ablation)LoCaSE · RSF main (train/test split)PLCC: 0.728 -> 0.576 (MeshCNN), 0.541 (DiffusionNet), 0.592 (PointNet++), 0.699 (DGCNN)Hurt
set LoRA rank to 32 instead of 8 or 16 (ablation)LoCaSE · RSF main (train/test split)SROCC: 0.7256 -> 0.7573 (rank 8 vs 32)Improved
increase LoRA rank from 32 to 64 (ablation)LoCaSE · RSF main (train/test split)SROCC: 0.7573 -> 0.7274No clear effect
weight Smooth L1 loss 5 versus PLCC and SROCC losses 1 each (ablation)LoCaSE · RSF main (train/test split)PLCC: 0.677 -> 0.728Improved
use LoCaSE instead of Chamfer Distance on unseen objects and methodsLoCaSE · RSF test-onlyPLCC: -0.46 -> 0.68Improved

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