paper-with-me

Papers

Multi-Sample Consensus Driven Unsupervised Normal Estimation for 3D Point Clouds

2023-04-10 · Jie Zhang, Minghui Nie, Junjie Cao, Jian Liu, Ligang Liu

Deep normal estimators have made great strides on synthetic benchmarks. Unfortunately, their performance dramatically drops on the real scan data since they are supervised only on synthetic datasets. The point-wise annotation of ground truth normals is vulnerable to inefficiency and inaccuracies, which totally makes it impossible to build perfect real datasets for supervised deep learning. To overcome the challenge, we propose a multi-sample consensus paradigm for unsupervised normal estimation. The paradigm consists of multi-candidate sampling, candidate rejection, and mode determination. The latter two are driven by neighbor point consensus and candidate consensus respectively. Two primary implementations of the paradigm, MSUNE and MSUNE-Net, are proposed. MSUNE minimizes a candidate consensus loss in mode determination. As a robust optimization method, it outperforms the cutting-edge supervised deep learning methods on real data at the cost of longer runtime for sampling enough candidate normals for each query point. MSUNE-Net, the first unsupervised deep normal estimator as far as we know, significantly promotes the multi-sample consensus further. It transfers the three online stages of MSUNE to offline training. Thereby its inference time is 100 times faster. Besides that, more accurate inference is achieved, since the candidates of query points from similar patches can form a sufficiently large candidate set implicitly in MSUNE-Net. Comprehensive experiments demonstrate that the two proposed unsupervised methods are noticeably superior to some supervised deep normal estimators on the most common synthetic dataset. More importantly, they show better generalization ability and outperform all the SOTA conventional and deep methods on three real datasets: NYUV2, KITTI, and a dataset from PCV [1].

📄 PDF Abstract BibTeX arXiv:2304.04884

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

HeMoRa: Unsupervised Heuristic Consensus Sampling for Robust Point Cloud Registration

2025-01-01 · CVPR 2025 1 · Shaocheng Yan, Yiming Wang, Kaiyan Zhao, Pengcheng Shi 외

Heuristic information for consensus set sampling is essential for correspondence-based point cloud registration, but existing approaches typically rely on supervised learning or expert-driven parameter tuning. In thi…

Point Cloud Registration

Anomaly Detection in Soil Heavy Metal Contamination Using Unsupervised Learning for Environmental Risk Assessment

2026-04-29 · Isaac Tettey Adjokatse, Samuel Senyo Koranteng, George Yamoah Afrifa, Theophilus Ansah-Narh 외 arxiv

Soil contamination by heavy metals poses a persistent environmental and public health concern in rapidly urbanising regions of Ghana, particularly at unregulated waste disposal sites. This study applies an unsupervised m…

Anomaly Detection

Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus

2020-10-02 · Marius Leordeanu, Mihai Pirvu, Dragos Costea, Alina Marcu 외

We address the challenging problem of semi-supervised learning in the context of multiple visual interpretations of the world by finding consensus in a graph of neural networks. Each graph node is a scene interpretation …

Scene UnderstandingSemantic Segmentation

FANFOLD: Graph Normalizing Flows-driven Asymmetric Network for Unsupervised Graph-Level Anomaly Detection

2024-06-29 · Rui Cao, Shijie Xue, Jindong Li, Qi Wang 외

Unsupervised graph-level anomaly detection (UGAD) has attracted increasing interest due to its widespread application. In recent studies, knowledge distillation-based methods have been widely used in unsupervised anomaly…

Anomaly DetectionKnowledge DistillationUnsupervised Anomaly Detection

Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs

2026-04-11 · Yiming Huang, Zhenbo Shi, Xin-Cheng Wen, Jichuan Zeng 외 arxiv

Unsupervised reinforcement learning (RL) has emerged as a promising paradigm for enabling self-improvement in large language models (LLMs). However, existing unsupervised RL-based methods often lack the capacity to adapt…

Reinforcement LearningMathematical Reasoning