← Search

Shicai Fan

7 accepted papers

2026

Density-Aware Point Cloud Upsampling via Relational Graph Flow Matching

RA-L 2026

Real-world point clouds exhibit non-uniform density distributions, varying across distance and scale. Conventional upsampling methods typically treat points homogeneously, which over-smooths sparse regions while over-processing dense regions. We propose PURF, a density-aware point cloud upsampling f

Cited by 0SourceScholar
2025

GraphDAE-PU: Graph Denosing Auto-Encoder for Arbitrary-Scale Point Cloud Upsampling

ICASSP 2025accepted

Existing learning-based arbitrary-scale point cloud upsampling methods are usually challenged with limited point cloud feature representation and noise-sensitive refinement of coarse point cloud. In this paper, we introduce GraphDAE-PU, a novel framework for point cloud upsampling that addresses the…

Cited by 0SourceScholar
2024

Dual Rank-1 Tensor Attention Module for Convolutional Neural Networks

ICASSP 2024accepted

Channel-spatial attention mechanisms have been extensively investigated in computer vision. However, it is still a difficult problem that how to efficiently utilize global and local contextual information laid in a feature tensor to generate an accurate 3D attention map. This paper proposes a novel…

Cited by 1SourceScholar
2024

MERSYS: A Collaborative Estimation and Dense Mapping System for Multi-Agent Generic SLAM

IROS 2024poster

Multi-agent collaborative Simultaneous Localization and Mapping (SLAM) is an effective way for large-scale mapping. However, this approach, which relies on Visual-Inertial Odometry(VIO) as input, suffers from limitations such as susceptibility to environmental influences and the difficulty in accura…

Cited by 0SourceScholar
2024

Unsupervised Anomaly Detection via Masked Diffusion Posterior Sampling

IJCAI 2024poster

Reconstruction-based methods have been commonly used for unsupervised anomaly detection, in which a normal image is reconstructed and compared with the given test image to detect and locate anomalies. Recently, diffusion models have shown promising applications for anomaly detection due to their pow…

Cited by 3SourcePDFScholar
2022

Constrained Adaptive Projection with Pretrained Features for Anomaly Detection

IJCAI 2022poster

Anomaly detection aims to separate anomalies from normal samples, and the pretrained network is promising for anomaly detection. However, adapting the pretrained features would be confronted with the risk of pattern collapse when finetuning on one-class training data. In this paper, we propose an an…