Learning to utilize image second-order derivative information for crisp edge detection

• URL: http://arxiv.org/abs/2406.05779v3
• Date: Fri, 28 Jun 2024 14:53:06 GMT
• Title: Learning to utilize image second-order derivative information for crisp edge detection
• Authors: Changsong Liu, Wei Zhang, Yanyan Liu, Yimeng Fan, Mingyang Li, Wenlin Li,
• Abstract summary: Edge detection is a fundamental task in computer vision. Recent top-performing edge detection methods tend to generate thick and noisy edge lines. We propose a second-order derivative-based multi-scale contextual enhancement module (SDMCM) to help the model locate true edge pixels accurately. We also construct a hybrid focal loss function (HFL) to alleviate the imbalanced distribution issue. In the end, we propose a U-shape network named LUS-Net which is based on the SDMCM and BRM for edge detection.
• Score: 13.848361661516595
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Edge detection is a fundamental task in computer vision. It has made great progress under the development of deep convolutional neural networks (DCNNs), some of which have achieved a beyond human-level performance. However, recent top-performing edge detection methods tend to generate thick and noisy edge lines. In this work, we solve this problem from two aspects: (1) the lack of prior knowledge regarding image edges, and (2) the issue of imbalanced pixel distribution. We propose a second-order derivative-based multi-scale contextual enhancement module (SDMCM) to help the model locate true edge pixels accurately by introducing the edge prior knowledge. We also construct a hybrid focal loss function (HFL) to alleviate the imbalanced distribution issue. In addition, we employ the conditionally parameterized convolution (CondConv) to develop a novel boundary refinement module (BRM), which can further refine the final output edge maps. In the end, we propose a U-shape network named LUS-Net which is based on the SDMCM and BRM for crisp edge detection. We perform extensive experiments on three standard benchmarks, and the experiment results illustrate that our method can predict crisp and clean edge maps and achieves state-of-the-art performance on the BSDS500 dataset (ODS=0.829), NYUD-V2 dataset (ODS=0.768), and BIPED dataset (ODS=0.903).

Related papers

• Generative Edge Detection with Stable Diffusion [52.870631376660924]
  Edge detection is typically viewed as a pixel-level classification problem mainly addressed by discriminative methods. We propose a novel approach, named Generative Edge Detector (GED), by fully utilizing the potential of the pre-trained stable diffusion model. We conduct extensive experiments on multiple datasets and achieve competitive performance.
  arXiv  Detail & Related papers  (2024-10-04T01:52:23Z)
• Cycle Pixel Difference Network for Crisp Edge Detection [12.642567744605183]
  This paper proposes a novel cycle pixel difference convolution (CPDC), which integrates image gradient information with modern convolution operations. To address the issue of edge thickness produced by most existing methods, we construct a multi-scale information enhancement module (MSEM) Our approach provides a novel perspective for addressing these challenges in edge detection.
  arXiv  Detail & Related papers  (2024-09-06T13:28:05Z)
• NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection [72.0098999512727]
  NeRF-Det has achieved impressive performance in indoor multi-view 3D detection by utilizing NeRF to enhance representation learning. We present three corresponding solutions, including semantic enhancement, perspective-aware sampling, and ordinal depth supervision. The resulting algorithm, NeRF-Det++, has exhibited appealing performance in the ScanNetV2 and AR KITScenes datasets.
  arXiv  Detail & Related papers  (2024-02-22T11:48:06Z)
• DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection [20.278655159290302]
  We propose the first diffusion model for the task of general edge detection, which we call DiffusionEdge. To avoid expensive computational resources while retaining the final performance, we apply DPM in the latent space and enable the classic cross-entropy loss. With all the technical designs, DiffusionEdge can be stably trained with limited resources, predicting crisp and accurate edge maps with much fewer augmentation strategies.
  arXiv  Detail & Related papers  (2024-01-04T02:20:54Z)
• Improving Pixel-based MIM by Reducing Wasted Modeling Capability [77.99468514275185]
  We propose a new method that explicitly utilizes low-level features from shallow layers to aid pixel reconstruction. To the best of our knowledge, we are the first to systematically investigate multi-level feature fusion for isotropic architectures. Our method yields significant performance gains, such as 1.2% on fine-tuning, 2.8% on linear probing, and 2.6% on semantic segmentation.
  arXiv  Detail & Related papers  (2023-08-01T03:44:56Z)
• Learning Weighting Map for Bit-Depth Expansion within a Rational Range [64.15915577164894]
  Bit-depth expansion (BDE) is one of the emerging technologies to display high bit-depth (HBD) image from low bit-depth (LBD) source. Existing BDE methods have no unified solution for various BDE situations. We design a bit restoration network (BRNet) to learn a weight for each pixel, which indicates the ratio of the replenished value within a rational range.
  arXiv  Detail & Related papers  (2022-04-26T02:27:39Z)
• One-Stage Deep Edge Detection Based on Dense-Scale Feature Fusion and Pixel-Level Imbalance Learning [5.370848116287344]
  We propose a one-stage neural network model that can generate high-quality edge images without postprocessing. The proposed model adopts a classic encoder-decoder framework in which a pre-trained neural model is used as the encoder. We propose a new loss function that addresses the pixel-level imbalance in the edge image.
  arXiv  Detail & Related papers  (2022-03-17T15:26:00Z)
• Adaptive Context-Aware Multi-Modal Network for Depth Completion [107.15344488719322]
  We propose to adopt the graph propagation to capture the observed spatial contexts. We then apply the attention mechanism on the propagation, which encourages the network to model the contextual information adaptively. Finally, we introduce the symmetric gated fusion strategy to exploit the extracted multi-modal features effectively. Our model, named Adaptive Context-Aware Multi-Modal Network (ACMNet), achieves the state-of-the-art performance on two benchmarks.
  arXiv  Detail & Related papers  (2020-08-25T06:00:06Z)
• Learning Crisp Edge Detector Using Logical Refinement Network [29.59728791893451]
  We propose a novel logical refinement network for crisp edge detection, which is motivated by the logical relationship between segmentation and edge maps. The network consists of a joint object and edge detection network and a crisp edge refinement network, which predicts more accurate, clearer and thinner high quality binary edge maps.
  arXiv  Detail & Related papers  (2020-07-24T11:12:48Z)
• Saliency Enhancement using Gradient Domain Edges Merging [65.90255950853674]
  We develop a method to merge the edges with the saliency maps to improve the performance of the saliency. This leads to our proposed saliency enhancement using edges (SEE) with an average improvement of at least 3.4 times higher on the DUT-OMRON dataset. The SEE algorithm is split into 2 parts, SEE-Pre for preprocessing and SEE-Post pour postprocessing.
  arXiv  Detail & Related papers  (2020-02-11T14:04:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.