Multi-scale Colorectal Tumour Segmentation Using a Novel Coarse to Fine Strategy

AbstractThe task of reconstructing detailed 3D human body models from images is interesting but challenging in computer vision due to the high freedom of human bodies. This work proposes a coarse-to-fine method to reconstruct detailed 3D human body from multi-view images combining Voxel Super-Resolution (VSR) based on learning the implicit representation. Firstly, the coarse 3D models are estimated by learning an Pixel-aligned Implicit Function based on Multi-scale Features (MF-PIFu) which are extracted by multi-stage hourglass networks from the multi-view images. Then, taking the low resolution voxel grids which are generated by the coarse 3D models as input, the VSR is implemented by learning an implicit function through a multi-stage 3D convolutional neural network. Finally, the refined detailed 3D human body models can be produced by VSR which can preserve the details and reduce the false reconstruction of the coarse 3D models. Benefiting from the implicit representation, the training process in our method is memory efficient and the detailed 3D human body produced by our method from multi-view images is the continuous decision boundary with high-resolution geometry. In addition, the coarse-to-fine method based on MF-PIFu and VSR can remove false reconstructions and preserve the appearance details in the final reconstruction, simultaneously. In the experiments, our method quantitatively and qualitatively achieves the competitive 3D human body models from images with various poses and shapes on both the real and synthetic datasets.

Download Full-text

Multi-scale vector quantization with reconstruction trees

Information and Inference A Journal of the IMA ◽

10.1093/imaiai/iaa004 ◽

2020 ◽

Author(s):

Enrico Cecini ◽

Ernesto De Vito ◽

Lorenzo Rosasco

Keyword(s):

Differential Geometry ◽

Decision Trees ◽

Vector Quantization ◽

Concentration Of Measure ◽

Finite Sample ◽

Multi Scale ◽

Unknown Distribution ◽

Coarse To Fine ◽

Special Case

Abstract We propose and study a multi-scale approach to vector quantization (VQ). We develop an algorithm, dubbed reconstruction trees, inspired by decision trees. Here the objective is parsimonious reconstruction of unsupervised data, rather than classification. Contrasted to more standard VQ methods, such as $k$-means, the proposed approach leverages a family of given partitions, to quickly explore the data in a coarse-to-fine multi-scale fashion. Our main technical contribution is an analysis of the expected distortion achieved by the proposed algorithm, when the data are assumed to be sampled from a fixed unknown distribution. In this context, we derive both asymptotic and finite sample results under suitable regularity assumptions on the distribution. As a special case, we consider the setting where the data generating distribution is supported on a compact Riemannian submanifold. Tools from differential geometry and concentration of measure are useful in our analysis.

Download Full-text

Multi-Scale Guided Mask Refinement for Coarse-to-Fine RGB-D Perception

IEEE Signal Processing Letters ◽

10.1109/lsp.2018.2886470 ◽

2019 ◽

Vol 26 (2) ◽

pp. 217-221 ◽

Cited By ~ 1

Author(s):

Chongyu Chen ◽

Haoguang Huang ◽

Chuangrong Chen ◽

Zhuoqi Zheng ◽

Hui Cheng

Keyword(s):

Multi Scale ◽

Coarse To Fine

Download Full-text

AN EFFECTIVE FRAMEWORK FOR AUTOMATIC SEGMENTATION OF HARD EXUDATES IN FUNDUS IMAGES

Journal of Circuits System and Computers ◽

10.1142/s0218126612500752 ◽

2013 ◽

Vol 22 (01) ◽

pp. 1250075 ◽

Cited By ~ 3

Author(s):

NAN YANG ◽

HU-CHUAN LU ◽

GUO-LIANG FANG ◽

GANG YANG

Keyword(s):

Automatic Segmentation ◽

Segmentation Algorithm ◽

Svm Classifier ◽

Fundus Images ◽

Subtraction Method ◽

Hard Exudates ◽

Double Ring ◽

Multi Scale ◽

Channel Information ◽

Coarse To Fine

In this paper, we propose an effective framework to automatically segment hard exudates (HEs) in fundus images. Our framework is based on a coarse-to-fine strategy, as we first get a coarse result allowed of some negative samples, then eliminate the negative samples step by step. In our framework, we make the most of the multi-channel information by employing a boosted soft segmentation algorithm. Additionally, we develop a multi-scale background subtraction method to obtain the coarse segmentation result. After subtracting the optical disc (OD) region from the coarse result, the HEs are extracted by a SVM classifier. The main contributions of this paper are: (1) propose an efficient and robust framework for automatic HEs segmentation; (2) present a boosted soft segmentation algorithm to combine multi-channel information; (3) employ a double ring filter to segment and adjust the OD region. We perform our experiments on the pubic DIARETDB1 dateset, which consists of 89 fundus images. The performance of our algorithm is assessed on both lesion-based criterion and image-based criterion. Our experimental results show that the proposed algorithm is very effective and robust.

Download Full-text

Coarse-to-fine localization of anatomical landmarks in CT images based on multi-scale local appearance and rotation-invariant spatial landmark distribution model

10.1117/12.2007134 ◽

2013 ◽

Author(s):

Mitsutaka Nemoto ◽

Yoshitaka Masutani ◽

Shouhei Hanaoka ◽

Yukihiro Nomura ◽

Soichiro Miki ◽

...

Keyword(s):

Ct Images ◽

Distribution Model ◽

Anatomical Landmarks ◽

Rotation Invariant ◽

Multi Scale ◽

Coarse To Fine ◽

Fine Localization

Download Full-text

Unsupervised Change Detection from Remotely Sensed Images Based on Multi-Scale Visual Saliency Coarse-to-Fine Fusion

Remote Sensing ◽

10.3390/rs13040630 ◽

2021 ◽

Vol 13 (4) ◽

pp. 630

Author(s):

Pengfei He ◽

Xiangwei Zhao ◽

Yuli Shi ◽

Liping Cai

Keyword(s):

Change Detection ◽

Visual Saliency ◽

Ground Truth ◽

Remotely Sensed ◽

Human Vision ◽

Scale Analysis ◽

Difference Image ◽

Multi Scale ◽

Remotely Sensed Images ◽

Coarse To Fine

Unsupervised change detection(CD) from remotely sensed images is a fundamental challenge when the ground truth for supervised learning is not easily available. Inspired by the visual attention mechanism and multi-level sensation capacity of human vision, we proposed a novel multi-scale analysis framework based on multi-scale visual saliency coarse-to-fine fusion (MVSF) for unsupervised CD in this paper. As a preface of MVSF, we generalized the connotations of scale as four classes in the field of remote sensing (RS) covering the RS process from imaging to image processing, including intrinsic scale, observation scale, analysis scale and modeling scale. In MVSF, superpixels were considered as the primitives for analysing the difference image(DI) obtained by the change vector analysis method. Then, multi-scale saliency maps at the superpixel level were generated according to the global contrast of each superpixel. Finally, a weighted fusion strategy was designed to incorporate multi-scale saliency at a pixel level. The fusion weight for the pixel at each scale is adaptively obtained by considering the heterogeneity of the superpixel it belongs to and the spectral distance between the pixel and the superpixel. The experimental study was conducted on three bi-temporal remotely sensed image pairs, and the effectiveness of the proposed MVSF was verified qualitatively and quantitatively. The results suggest that it is not entirely true that finer scale brings better CD result, and fusing multi-scale superpixel based saliency at a pixel level obtained a higher F1 score in the three experiments. MVSF is capable of maintaining the detailed changed areas while resisting image noise in the final change map. Analysis of the scale factors in MVSF implied that the performance of MVSF is not sensitive to the manually selected scales in the MVSF framework.

Download Full-text