ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Photo

Lei, Biwen; Guo, Xiefan; Yang, Hongyu; Cui, Miaomiao; Xie, Xuansong; Huang, Di

doi:10.1109/cvpr52688.2022.00215

Cited by 7 publications

(6 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Determining the parameters of the optimal Gaussian distribution while simultaneously optimising the NF model. To enhance the precision of high-resolution defect localisation, PyramidFlow [32] incorporates the pyramid NF to address features across various scales, thereby augmenting defect perception.…”

Section: Feature Distribution-based Methodsmentioning

confidence: 99%

MBMF: Constructing memory banks of multi‐scale features for anomaly detection

Sun,

Wang,

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

In industrial manufacturing, how to accurately classify defective products and locate the location of defects has always been a concern. Previous studies mainly measured similarity based on extracting single‐scale features of samples. However, only using the features of a single scale is hard to represent different sizes and types of anomalies. Therefore, the authors propose a set of memory banks of multi‐scale features (MBMF) to enrich feature representation and detect and locate various anomalies. To extract features of different scales, different aggregation functions are designed to produce the feature maps at different granularity. Based on the multi‐scale features of normal samples, the MBMF are constructed. Meanwhile, to better adapt to the feature distribution of the training samples, the authors proposed a new iterative updating method for the memory banks. Testing on the widely used and challenging dataset of MVTec AD, the proposed MBMF achieves competitive image‐level anomaly detection performance (Image‐level Area Under the Receiver Operator Curve (AUROC)) and pixel‐level anomaly segmentation performance (Pixel‐level AUROC). To further evaluate the generalisation of the proposed method, we also implement anomaly detection on the BeanTech AD dataset, a commonly used dataset in the field of anomaly detection, and the Fashion‐MNIST dataset, a widely used dataset in the field of image classification. The experimental results also verify the effectiveness of the proposed method.

show abstract

Section: Feature Distribution-based Methodsmentioning

confidence: 99%

MBMF: Constructing memory banks of multi‐scale features for anomaly detection

Sun,

Wang,

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…To address blemishes at large scale, BPFRe (Xie et al 2023) adopted a two-stage retouching strategy to progressively restore clean face. ABPN (Lei et al 2022) propose an adaptive blend pyramid network, which achieved fast local retouching on high-resolution photos.…”

Section: Face Retouchingmentioning

confidence: 99%

“…Ling et al 2021), image enhancement (Zamir et al 2021;Yang et al 2021;Wang et al 2022), and so on. AutoRetouch (Shafaei, Little, and Schmidt 2021) and ABPN (Lei et al 2022) start to focus on face retouching. However, these methods only consider image-level transformations by global convolution filters, and the imperfection regions cannot be adaptively completed.…”

Section: Introductionmentioning

confidence: 99%

RetouchFormer: Semi-supervised High-Quality Face Retouching Transformer with Prior-Based Selective Self-Attention

Wen,

Xie,

Jiang

et al. 2024

AAAI

View full text Add to dashboard Cite

Face retouching is to beautify a face image, while preserving the image content as much as possible. It is a promising yet challenging task to remove face imperfections and fill with normal skin. Generic image enhancement methods are hampered by the lack of imperfection localization, which often results in incomplete removal of blemishes at large scales. To address this issue, we propose a transformer-based approach, RetouchFormer, which simultaneously identify imperfections and synthesize realistic content in the corresponding regions. Specifically, we learn a latent dictionary to capture the clean face priors, and predict the imperfection regions via a reconstruction-oriented localization module. Also based on this, we can realize face retouching by explicitly suppressing imperfections in our selective self-attention computation, such that local content will be synthesized from normal skin. On the other hand, multi-scale feature tokens lead to increased flexibility in dealing with the imperfections at various scales. The design elements bring greater effectiveness and efficiency. RetouchFormer outperforms the advanced face retouching methods and synthesizes clean face images with high fidelity in our list of extensive experiments performed.

show abstract

“…However, the actual skin texture is full of high-frequency details such as moles, scars, freckles, and other blemishes, which bring ambiguities to the geometry details learning especially in the single view FR task. Inspired by the [32], we propose a de-retouching module (DRM), which aims to generate the face albedo with highfrequency details and facilitate more precise decoupling of geometry and appearance.…”

Section: De-retouching Modulementioning

confidence: 99%

“…Moreover, we introduce the 3D priors of MF and HF details by fitting face scans with our hierarchical representation to facilitate accurate and faithful modeling. Inspired by [32], we propose a de-retouching module to adaptively refine the base texture to overcome the ambiguities between skin blemishes and illuminations. Extensive experiments show that our method outperforms the existing methods on two large-scale benchmarks, exhibiting excellent performance in terms of detail capturing and accurate shape modeling.…”

Section: Introductionmentioning

confidence: 99%