mlsanityData to 7 Oct 2026

Deep Learning Approaches for 3D Medical Scene Completion: From Geometric Modeling to Generative Paradigms

arXiv 2606.24180 ↗First posted 23 Jun 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Three-dimensional scene completion has evolved as a major problem in computer vision and robotics, and its applications are diverse, including autonomous navigation and augmented reality. In this study, a systematic review has been conducted to compile the research contributions made in the last ten years, i.e., 2016 to 2026, which has revolutionized the field from the voxel semantic completion paradigm represented by SSCNet to the latest paradigm that combines generative diffusion priors with real-time rendering using a Gaussian splatting technique. The evolution in representation paradigms, such as voxel grids, point learning, implicit neural fields, transformer networks, diffusion networks, and the latest paradigm based on rendering-aware 3D Gaussian primitives, has been discussed in this study. A comprehensive analysis has been carried out on the contributions made in the last ten years, and a taxonomy has been developed to provide a clear idea about the contributions made in the field. The study has also discussed the research contributions made in the field, along with the challenges that still need to be addressed. Finally, the study has presented a research agenda that will provide a clear idea about the directions that can be followed in the development of the next-generation system

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 53 of its 89 references that are in the map. First posted on arXiv 23 Jun 2026.

Builds on

53 of 89 references.

References · 53

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  9. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  10. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  11. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
38 more
  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  3. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  4. 2020Point Transformercited by 1,462
  5. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  6. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  7. 2020Convolutional Occupancy Networkscited by 760
  8. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  9. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  10. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  11. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  12. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  13. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  14. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  15. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  16. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  17. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  18. 2018PCN: Point Completion Networkcited by 382
  19. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  20. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  21. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  22. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  23. 2017Submanifold Sparse Convolutional Networkscited by 223
  24. 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 199
  25. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  26. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 162
  27. 2016Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planningcited by 148
  28. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  29. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 146
  30. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  31. 2014Learning Rich Features from RGB-D Images for Object Detection and Segmentationcited by 124
  32. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  33. 2018Training and Inference with Integers in Deep Neural Networkscited by 84
  34. 2019Multi-view PointNet for 3D Scene Understandingcited by 76
  35. 2018Multi-Level Factorisation Net for Person Re-Identificationcited by 58
  36. 2023MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervisioncited by 18
  37. 2024GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstructioncited by 18
  38. 2022Point normal orientation and surface reconstruction by incorporating isovalue constraints to Poisson equationcited by 8

50 most cited of 53 All 53 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image
  2. 2025G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior
  3. 2025Generative Gaussian Splatting: Generating 3D Scenes with Video Diffusion Priors
  4. 2024Survey on Fundamental Deep Learning 3D Reconstruction Techniques
  5. 20253D Scene Generation: A Survey
  6. 2026FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation
  7. 2024Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors
  8. 2024Diffusion Models in 3D Vision: A Survey