EREric Rigall

Eric Rigall

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Eric Rigall has a total of 50 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • MAFSRM: A Multiangle Feature Separation and Reconstruction Module for Industrial Defect Detection

    by Zongshuai Zhang, Ying Gao, Lvwei Zhu, Eric Rigall, Xinjing Wang, Junyu Dong

    In industrial manufacturing, the measurability of surface defects directly impacts the accuracy of quality assessment and the effectiveness of process control. While object detection-based methods can rapidly localize defects, they often fall short in supporting high-fidelity visual measurement due to several critical challenges: the strict sub-second timing required by high-speed production lines, the interference from complex backgrounds that distorts geometric and edge information, and the low salience and diversity of small-scale defects, which hampers the extraction of stable, measurement-relevant features. To address these issues, we propose a plug-and-play Multi-Angle Feature Separation and Reconstruction Module (MAFSRM), designed to enhance the quality and robustness of defect features from a measurement perspective. MAFSRM consists of three submodules: (1) Spatial Pyramid Pooling-Fast Separation and Reconstruction (SPPFSR) for fast, scale-adaptive feature extraction; (2) Weight Separation and Reconstruction (WSR) for isolating defect regions from background interference in the spatial domain; (3) Feature Separation and Reconstruction (FSR) for enhancing defect distinctiveness by refining channel-level feature representations. The module can be seamlessly integrated into mainstream single-stage detection frameworks, enabling easy deployment without altering the existing pipeline. Experiments on NEU-DET, GC10-DET, PCB, and a self-constructed Tire-DET dataset show that MAFSRM significantly improves both detection accuracy and feature stability, offering highly reliable inputs for downstream measurements of defect size and morphology.

  • Region-Aware Driven Distribution Optimization for Stereo Matching

    by Lvwei Zhu, Eric Rigall, Ying Gao, Zongshuai Zhang, Yafei Bai, Junyu Dong

    Accurate disparity estimation in diverse and complex scenes remains a significant challenge in stereo matching, requiring precise geometric perception and robust generalization. Traditional methods often struggle in capturing fine-grained details and maintaining structural consistency under varying conditions, leading to a great reduction of the disparity estimation performance. To address these limitations, we propose Reg-Stereo, a novel framework based on region-aware distribution optimization. It leverages region-aware awakening to extract structural cues and explicitly optimizes the spatial distribution of feature responses. By strengthening relative structural attributes within local regions and expanding them to the global context, our approach enables a more precise and context-aware representation of geometric structures, effectively capturing fine details while preserving global consistency. This innovative approach enables the framework to adapt effectively to diverse and challenging environments, improving both robustness and generalization. Extensive experiments on multiple datasets validate the effectiveness of Reg-Stereo, surpassing exisitng state-of-the-art methods in disparity estimation with enhanced adaptability across complex and heterogeneous scenarios.


  • Open Access

    Underwater Target 3D Reconstruction via Integrated Laser Triangulation and Multispectral Photometric Stereo

    by Yang Yang, Yimei Liu, Eric Rigall, Yifan Yin, Shu Zhang, Junyu Dong

    With the gradual application of 3D reconstruction technology in underwater scenes, the design of vision-based reconstruction models has become an important research direction for human ocean exploration and development. The underwater laser triangulation method is the most commonly used approach, yet it misses details during the reconstruction of sparse point clouds, which do not meet the requirements of practical applications. On the other hand, existing underwater photometric stereo methods can accurately reconstruct local details of target objects, but they require relative stillness to be maintained between the camera and the target, which is practically difficult to achieve in underwater imaging environments. In this paper, we propose an underwater target reconstruction algorithm that combines laser triangulation and multispectral photometric stereo (MPS) to address the aforementioned practical problems in underwater 3D reconstruction.This algorithm can obtain more comprehensive 3D surface data of underwater objects through mobile measurement. At the same time, we propose to optimize the laser place calibration and laser line separation processes, further improving the reconstruction performance of underwater laser triangulation and multispectral photometric stereo. The experimental results show that our method achieves higher-precision and higher-density 3D reconstruction than current state-of-the-art methods.


  • A New Benchmark and Low Computational Cost Localization Method for Cephalometric Analysis

    by Xianglong Wang, Eric Rigall, Xifeng An, Zhihao Li, Qing Cai, Shu Zhang, Junyu Dong

    In this study, we present WebCeph2k, an extensive and diverse cephalometric landmark localization dataset that surpasses previous benchmark datasets in terms of number of landmark annotations. This diverse cephalometric landmarks dataset has significant value in medical imaging research. Existing studies predominantly focus on datasets obtained from a single medical center and provider, which offers a limited number of landmarks and a limited diversity of cephalograms, resulting in models that exhibit low robustness and generalization when applied to more diverse datasets. The clinical application of cephalometry is hampered by significant localization errors in landmark localization models, in addition to the inadequacy of existing datasets’ landmarks for clinical cephalometric diagnosis. The limited generalization ability and the occurrence of “overfitting” in deep learning models are mainly caused by the small size in the dataset. In the medical field, the inclusion of large and diverse datasets can greatly improve the generalization and performance of landmark localization models. This paper presents our WebCeph2k dataset from 9 medical centers, covering 9 different imaging devices, which surpasses the only publicly available ISBI2015 dataset in terms of sample size and number of landmarks. In addition, this study employs a low computational cost methodology to achieve optimal landmarks localization: 1) ROI regions of X-ray images are derived by exploiting the prior distribution of the data, 2) the model computational cost is reduced by adopting a spatial-depth transformation strategy, 3) the standard heatmap decoding method is optimized by integrating a compensation strategy. The results show that the proposed method not only achieves competitive localization results to other state-of-the-art approaches, but also offers a reduction of the model computational cost, resulting in faster inference. Consequently, this research offers valuable prospects in the field of general-purpose medical landmark localization methods. We also find that our proposed dataset is more complex and challenging than the ISBI dataset. The dataset and code are available at https://github.com/switch626/WebCeph2k.


  • Point Light Measurement and Calibration for Photometric Stereo

    by Yang Yang, Eric Rigall, Hao Fan, Junyu Dong

    Accurate measurement and calibration of the light position or the lighting direction is essential for pixel-level 3D reconstruction based on Photometric Stereo. Differing from previous methods using Lambert ball or mirror ball for measurement and calibration, we employ a standard block with a related shadow model for more accurate estimation of light positions. In essence, we propose a new measurement and calibration method that calculates the point light position from the triangulation relations between the lighting direction and the shadow, while the standard block is placed on a white flat plane under a fixed light. In this way, we can calibrate the pose of the point light source from the shadow model in all lighting directions. In addition, the lighting direction from the far-point source is also analyzed and solved. In our experiments, we apply the proposed scheme to Photometric Stereo and Multi-spectral Photometric Stereo. Experimental results not only validate the accuracy of our method but also help us to further reveal the effects of slant and tilt angles of the lighting directions on 3D Reconstruction based on Photometric Stereo.


  • Open Access

    A Method for Breast Mass Segmentation using Image Augmentation with SAM and Receptive Field Expansion

    by Binjun Zhang, Eric Rigall, Yuting Huang, Xiao Zou, Shu Zhang, Junyu Dong, Hui Yu

    With the development of deep learning methods and their wide application in medical image segmentation tasks, mammography, used for early breast cancer screening, can further assist clinicians in diagnosis to a certain extent. Due to the loss of fine-grained features in the downsampling process and the very few available mammograms, the main methods for extracting masses from the whole mammography are relatively ineffective. In this paper, we propose a novel mass segmentation model for mammograms based on two U-Net network models, and integrate the Receptive Field Block (RFB) module in-between to enhance the deep features captured by the model. We augmented the input image using Segment Anything Model (SAM) and evaluated the proposed architecture on two public datasets, namely the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) and INBreast, as well as on a private dataset. The results show that the proposed model for segmenting masses in ROI regions can achieve high Dice scores of 92.18% and 89.85%, and Intersection over Union (IoU) scores of 85.47% and 80.80% on both INBreast and the private dataset. In addition, our model for segmenting masses on whole mammographs in CBIS-DDSM dataset can achieve Dice scores of 58.10% and 41.96% IoU scores. Besides, our model performance improved to Dice score 61.78% and IoU score 43.00% on whole mammographs in private dataset using SAM-augmented input images.


  • Learning General Descriptors for Image Matching With Regression Feedback

    by Yuan Rao, Yakun Ju, Cong Li, Eric Rigall, Jian Yang, Hao Fan, Junyu Dong

    Recent advances on feature descriptors for image matching put more emphasis on encoding invariances ( e.g . illumination invariance) to promote the descriptors’ discriminative power. However, according to the information entropy, more invariance implies greater certainty and less informativeness in a descriptor. Consequently, descriptors encoding too many invariances usually show poor generalization to unknown image changes, lacking enough informativeness to cover the large uncertainty in unseen scenes. This limits the application scenarios of learned descriptors. In this paper, we propose to alleviate this issue from the perspective of informativeness and we thus design hierarchical consistent constraint by introducing regression feedback in a self-supervised manner. Combined with the hardest-within-batch matching constraint, we form a novel dual supervision framework, to encourage the descriptor to learn an informative representation while maintaining a good discriminative power. Moreover, to fully mine the context information hidden in image and boost the informativeness in turn, we present AANet, a descriptor network that efficiently predicts dense description by the powerful Attentional Aggregation of multi-level features. Experiments across challenging feature matching on HPatches, RDNIM datasets, and visual localization tasks on Aachen Day-night dataset show that our method outperforms recent state-of-the-art descriptors while keeping encouraging efficiency. The application of visual 3D reconstruction on various scenarios also demonstrates the high generalization ability of our method.


  • Incorporating Co-Visibility Reasoning Into Surface Depth Measurement

    by Yimei Liu, Yuan Rao, Eric Rigall, Hao Fan, Junyu Dong

    Multi-view stereo (MVS) aims to measure the precise surface depth of a scene from observations at multiple photography angles and then densely reconstruct its 3D geometry information. Learning-based MVS approaches have been dominantly popular for their robustness to low texture areas and non-Lambertian surfaces. However, most existing methods focus on estimating depth maps for input images by constructing global cost volumes and designing ingenious yet large variance-based 3D-CNN networks for cost volume regularization. Such approaches ignore the co-visible relation embedded in multiple views, resulting in heavy computation, erroneous cost aggregation from invisible views, and finally inaccurate 3D reconstruction results. In this paper, we propose a Co-visibility Reasoning Multi-View Stereo Network (CR-MVSNet) to explore the co-visible relations hidden in multiple views for reliable multi-view similarity measurement and efficient reconstruction. Precisely, the proposed Co-visibility Reasoning Cost Aggregation (CRCA) module includes the adaptive inter-cost volume aggregation via mining the uncertainty of co-visibility relations in multiple views and the adaptive intra-cost volume aggregation by exploiting spatial contextual information. Moreover, the cost volumes are constructed via the proposed global-to-patch manner to speed up computation. Experimental results show that our approach achieves the best overall performance on the DTU, Tanks and Temples, and ETH3D-test datasets over recent state-of-the-art MVS algorithms. The consistently favorable results on three datasets with completely different depth ranges proved the superiority and generalizability of CR-MVSNet.


  • Transmittance Surface Detection and Material Identification Using Multitask ViT-SIFT Fusion

    by Amanuel Hirpa Madessa, Junyu Dong, Eric Rigall, Qingxuan Lv, Hafiza Sadia Nawaz Nawaz, Israel Mugunga, Shaoxiang Guo

    The automatic detection of transmittance surfaces (transparency and translucency) and material class identification (glass, plastic, etc.) from an image is crucial for applications including domestic service robotics and handling fragile instruments in experimental or industrial settings. However, this is a difficult task due to the lack of expressive textures in such materials. Although previous approaches for detecting transmittance surfaces propose handcrafted features, they disregard global material information and are limited to a single item (usually glass). Material or object recognition algorithms based on Convolutional Neural Networks (CNN) focus on optimizing performance that requires large labeled datasets. These algorithms are better for detecting opaque objects because large architectures tend to generalize the texture from an image’s background layer. Furthermore, creating large scale off-the-shelf dataset labeled with transmittance surface is extremely tedious task. Thus, we propose a simple yet effective and efficient learning model that combines a shallow multi-task Vision Transformer (ViT) with a Scale Invariant Feature Transform (SIFT) and a shallow CNN as the backbone network. SIFT and ViT are used to capture local and global discriminative features respectively, and their fusion can increase the performance on a small dataset. The backbone network is utilized to introduce desirable properties of CNN. Using limited training data, this model detects transmittance surfaces and determines their material type. We conducted tests on a new benchmark dataset containing a variety of transmissive materials and three publicly available datasets for robust comparison. Results show that the proposed model achieved a new state-of-the-art accuracy of 81.78% and 77.21% on our new dataset for transmittance surface recognition and material class identification respectively.