mlsanityData to 7 Oct 2026

3D Brain Reconstruction by Hierarchical Shape-Perception Network from a Single Incomplete Image

arXiv 2107.11010 ↗First posted 23 Jul 2021eess.IV cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

3D shape reconstruction is essential in the navigation of minimally-invasive and auto robot-guided surgeries whose operating environments are indirect and narrow, and there have been some works that focused on reconstructing the 3D shape of the surgical organ through limited 2D information available. However, the lack and incompleteness of such information caused by intraoperative emergencies (such as bleeding) and risk control conditions have not been considered. In this paper, a novel hierarchical shape-perception network (HSPN) is proposed to reconstruct the 3D point clouds (PCs) of specific brains from one single incomplete image with low latency. A branching predictor and several hierarchical attention pipelines are constructed to generate point clouds that accurately describe the incomplete images and then complete these point clouds with high quality. Meanwhile, attention gate blocks (AGBs) are designed to efficiently aggregate geometric local features of incomplete PCs transmitted by hierarchical attention pipelines and internal features of reconstructing point clouds. With the proposed HSPN, 3D shape perception and completion can be achieved spontaneously. Comprehensive results measured by Chamfer distance and PC-to-PC error demonstrate that the performance of the proposed HSPN outperforms other competitive methods in terms of qualitative displays, quantitative experiment, and classification evaluation.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 24 of its 73 references that are in the map. First posted on arXiv 23 Jul 2021.

Builds on

24 of 73 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  9. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  10. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  11. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  12. 2018PCN: Point Completion Networkcited by 382
12 more
  1. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  2. 2015Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Imagescited by 111
  3. 2020Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesiscited by 38
  4. 2020Fine Perceptive GANs for Brain MR Image Super-Resolution in Wavelet Domaincited by 24
  5. 2020Tensorizing GAN with High-Order Pooling for Alzheimer's Disease Assessmentcited by 21
  6. 2021Characterization Multimodal Connectivity of Brain Network by Hypergraph GAN for Alzheimer's Disease Analysiscited by 18
  7. 2020Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priorscited by 11
  8. 2019Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Viewscited by 10
  9. 2019One-stage Shape Instantiation from a Single 2D Image to 3D Point Cloudcited by 9
  10. 2021A Point Cloud Generative Model via Tree-Structured Graph Convolutions for 3D Brain Shape Reconstructioncited by 8
  11. 2018SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Networkcited by 6
  12. 2019Probabilistic Point Cloud Reconstructions for Vertebral Shape Analysiscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 2; 2025: 2; 2026: 1.

10 papers.

  1. 2023MedPrompt: Cross-Modal Prompting for Multi-Task Medical Image Translationcited by 13
  2. 2024CATD: Unified Representation Learning for EEG-to-fMRI Cross-Modal Generationcited by 11
  3. 2022Inflating 2D Convolution Weights for Efficient Generation of 3D Medical Imagescited by 8
  4. 2023Brain Structure-Function Fusing Representation Learning using Adversarial Decomposed-VAE for Analyzing MCIcited by 5
  5. 2024Multi-modal Mood Reader: Pre-trained Model Empowers Cross-Subject Emotion Recognitioncited by 4
  6. 2025From Pixels to Polygons: A Survey of Deep Learning Approaches for Medical Image-to-Mesh Reconstructioncited by 4
  7. 2023BDHT: Generative AI Enables Causality Analysis for Mild Cognitive Impairmentcited by 3
  8. 2025ConnectomeDiffuser: Generative AI Enables Brain Network Construction from Diffusion Tensor Imagingcited by 1
  9. 2023SG-GAN: Fine Stereoscopic-Aware Generation for 3D Brain Point Cloud Up-sampling from a Single Imagecited by 0
  10. 2026High-Fidelity 3D Geometric Reconstruction of Pelvic Organs from MRI: A Hybrid Deep Learning and Iterative Optimization Approachcited by 0