works on

From the 1 of 6 linked papers with an AI index.

collaborators

6 papers

cs.CV2026

CASA-SDF: Curriculum-Aware Spatial Adaptation with Curvature-Guided Density for Neural Implicit Surface Reconstruction

Lei Yang, Weiqing Li, Zhiyong Su +1

The paper introduces CASA-SDF, a framework that uses curriculum-aware spatial adaptation and curvature-guided density transformation to improve neural implicit surface reconstructi…

cs.CV2026

UGD: An Unsupervised Geometric Distance for Evaluating Real-world Noisy Point Cloud Denoising

Zhiyong Su, Jincan Wu, Yonghui Liu +2

Point cloud denoising is a fundamental and crucial challenge in real-world point cloud applications. Existing quantitative evaluation metrics for point cloud denoising methods are…

eess.IV2026

UPDA: Unsupervised Progressive Domain Adaptation for No-Reference Point Cloud Quality Assessment

Bingxu Xie, Fang Zhou, Jincan Wu +3

While no-reference point cloud quality assessment (NR-PCQA) approaches have achieved significant progress over the past decade, their performance often degrades substantially when…

cs.CV2025

Open-world Point Cloud Semantic Segmentation: A Human-in-the-loop Framework

Peng Zhang, Songru Yang, Jinsheng Sun +2

Open-world point cloud semantic segmentation (OW-Seg) aims to predict point labels of both base and novel classes in real-world scenarios. However, existing methods rely on resourc…

cs.CV2025

No-reference geometry quality assessment for colorless point clouds via list-wise rank learning

Zheng Li, Bingxu Xie, Chao Chu +2

Geometry quality assessment (GQA) of colorless point clouds is crucial for evaluating the performance of emerging point cloud-based solutions (e.g., watermarking, compression, and…

cs.CV2025

The Worse The Better: Content-Aware Viewpoint Generation Network for Projection-related Point Cloud Quality Assessment

Zhiyong Su, Bingxu Xie, Zheng Li +2

Through experimental studies, however, we observed the instability of final predicted quality scores, which change significantly over different viewpoint settings. Inspired by the…