Gaussian Filter in CRF Based Semantic Segmentation

2017-09-02 · Yichi Gu, Qisheng Wu, Jing Li, Kai Cheng

Artificial intelligence is making great changes in academy and industry with the fast development of deep learning, which is a branch of machine learning and statistical learning. Fully convolutional network [1] is the standard model for semantic segmentation. Conditional random fields coded as CNN [2] or RNN [3] and connected with FCN has been successfully applied in object detection [4]. In this paper, we introduce a multi-resolution neural network for FCN and apply Gaussian filter to the extended CRF kernel neighborhood and the label image to reduce the oscillating effect of CRF neural network segmentation, thus achieve higher precision and faster training speed.

📄 PDF Abstract BibTeX arXiv:1709.00516

Code (0)

등록된 구현이 없습니다.

Tasks

object-detection Object Detection Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

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…

CRF Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is…

FCN Fully Convolutional Networks, or FCNs, are an architecture used mainly for semantic segmentation. They employ solely locally connected layers, such as…

2D-Guided 3D Gaussian Segmentation

2023-12-26 · Kun Lan, Haoran Li, Haolin Shi, Wenjun Wu 외

Recently, 3D Gaussian, as an explicit 3D representation method, has demonstrated strong competitiveness over NeRF (Neural Radiance Fields) in terms of expressing complex scenes and training duration. These advantages sig…

NeRF Segmentation Semantic Segmentation

LabelGS: Label-Aware 3D Gaussian Splatting for 3D Scene Segmentation

2025-08-27 · Yupeng Zhang, Dezhi Zheng, Ping Lu, Han Zhang 외 arxiv

3D Gaussian Splatting (3DGS) has emerged as a novel explicit representation for 3D scenes, offering both high-fidelity reconstruction and efficient rendering. However, 3DGS lacks 3D segmentation ability, which limits its…

Scene Understanding Scene Segmentation

CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus

2025-09-05 · Hannah Schieber, Dominik Frischmann, Victor Schaack, Simon Boche 외 arxiv

Fast and efficient photorealistic 3D reconstruction with (semantic) Gaussian Splatting (GS) is crucial for time-critical robotic perception and navigation, where robots may need to rapidly reconstruct and inspect specifi…

3D Reconstruction

Clean-GS: Semantic Mask-Guided Pruning for 3D Gaussian Splatting

2026-01-01 · Subhankar Mishra arxiv

3D Gaussian Splatting produces high-quality scene reconstructions but generates hundreds of thousands of spurious Gaussians (floaters) scattered throughout the environment. These artifacts obscure objects of interest and…

Model Compression

Blurring Structure and Learning to Optimize and Adapt Receptive Fields

2019-09-25 · Evan Shelhamer, Dequan Wang, Trevor Darrell

The visual world is vast and varied, but its variations divide into structured and unstructured factors. We compose free-form filters and structured Gaussian filters, optimized end-to-end, to factorize deep representatio…

Form Semantic Segmentation