MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation

2019-02-12 · Chen Liu, Yasutaka Furukawa

We propose a new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance. The proposed network, built upon submanifold sparse convolution [3], processes a voxelized point cloud and predicts semantic scores for each occupied voxel as well as the affinity between neighboring voxels at different scales. A simple yet effective clustering algorithm segments points into instances based on the predicted affinity and the mesh topology. The semantic for each instance is determined by the semantic prediction. Experiments show that our method outperforms the state-of-the-art instance segmentation methods by a large margin on the widely used ScanNet benchmark [2]. We share our code publicly at https://github.com/art-programmer/MASC.

📄 PDF Abstract BibTeX arXiv:1902.04478

Code (1)

art-programmer/MASC 공식 구현 pytorch

Tasks

3D Instance SegmentationClusteringInstance Segmentation Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network

2018-08-01 · ECCV 2018 9 · Xinjing Cheng, Peng Wang, Ruigang Yang

Depth estimation from a single image is a fundamental problem in computer vision. In this paper, we propose a simple yet effective convolutional spatial propagation network (CSPN) to learn the affinity matrix for depth p…

Depth Estimation Depth Prediction

SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices

2026-06-05 · Ernests Lavrinovics, Marco Letizia, Roy Janco, Shai Segal 외 arxiv

We present SigmaScale, a method for learning auxiliary scaling matrices $S$ to aid truncated Singular Value Decomposition (SVD) based Large Language Model (LLM) compression. Instead of deriving scaling matrices analytica…

Deep Class-Specific Affinity-Guided Convolutional Network for Multimodal Unpaired Image Segmentation

2021-01-05 · Jingkun Chen, Wenqi Li, Hongwei Li, JianGuo Zhang

Multi-modal medical image segmentation plays an essential role in clinical diagnosis. It remains challenging as the input modalities are often not well-aligned spatially. Existing learning-based methods mainly consider s…

Image Segmentation Medical Image Segmentation Segmentation Semantic Segmentation

Sparse-Dense Subspace Clustering

2019-10-20 · Shuai Yang, Wenqi Zhu, Yuesheng Zhu

Subspace clustering refers to the problem of clustering high-dimensional data into a union of low-dimensional subspaces. Current subspace clustering approaches are usually based on a two-stage framework. In the first sta…

Clustering

Affinity Fusion Graph-based Framework for Natural Image Segmentation

2020-06-24 · Yang Zhang, Moyun Liu, Jingwu He, Fei Pan 외

This paper proposes an affinity fusion graph framework to effectively connect different graphs with highly discriminating power and nonlinearity for natural image segmentation. The proposed framework combines adjacency-g…

Clustering Image Segmentation Segmentation Semantic Segmentation+1