mlsanityData to 14 Oct 2026

3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow

arXiv 2203.15190 ↗First posted 29 Mar 2022cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

Reconstructing 3D shape from a single 2D image is a challenging task, which needs to estimate the detailed 3D structures based on the semantic attributes from 2D image. So far, most of the previous methods still struggle to extract semantic attributes for 3D reconstruction task. Since the semantic attributes of a single image are usually implicit and entangled with each other, it is still challenging to reconstruct 3D shape with detailed semantic structures represented by the input image. To address this problem, we propose 3DAttriFlow to disentangle and extract semantic attributes through different semantic levels in the input images. These disentangled semantic attributes will be integrated into the 3D shape reconstruction process, which can provide definite guidance to the reconstruction of specific attribute on 3D shape. As a result, the 3D decoder can explicitly capture high-level semantic features at the bottom of the network, and utilize low-level features at the top of the network, which allows to reconstruct more accurate 3D shapes. Note that the explicit disentangling is learned without extra labels, where the only supervision used in our training is the input image and its corresponding 3D shape. Our comprehensive experiments on ShapeNet dataset demonstrate that 3DAttriFlow outperforms the state-of-the-art shape reconstruction methods, and we also validate its generalization ability on shape completion task.

Key facts. Cited by 45 papers in the map (data through 14 Oct 2026). Builds on 44 of its 61 references that are in the map. First posted on arXiv 29 Mar 2022.

Builds on

44 of 61 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  9. 2020Point Transformercited by 1,470
  10. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  11. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  12. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
32 more
  1. 2014Show and Tell: A Neural Image Caption Generatorcited by 879
  2. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  3. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  4. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  5. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  6. 2018PCN: Point Completion Networkcited by 384
  7. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  8. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 164
  9. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  10. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  11. 2020Self-supervised Single-view 3D Reconstruction via Semantic Consistencycited by 127
  12. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  13. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
  14. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  15. 2021Variational Relational Point Completion Networkcited by 104
  16. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  17. 2020PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Pathscited by 97
  18. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  19. 2022PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Pathscited by 57
  20. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  21. 2022Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Cloudscited by 42
  22. 2020DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Imagescited by 35
  23. 2021EigenGAN: Layer-Wise Eigen-Learning for GANscited by 34
  24. 2018Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapescited by 25
  25. 2021SP-GAN: Sphere-Guided 3D Shape Generation and Manipulationcited by 21
  26. 2018MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Imagecited by 17
  27. 2020SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinatescited by 17
  28. 2019Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsulescited by 14
  29. 2018CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervisioncited by 12
  30. 20193DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attentioncited by 12
  31. 2019Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Viewscited by 10
  32. 2020LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contextscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 9; 2023: 14; 2024: 14; 2025: 6; 2026: 2.

45 papers.

Sort:

By area:

  1. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
  2. 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
  3. 2024DiffGS: Functional Gaussian Splatting Diffusioncited by 51
  4. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 47
  5. 2024Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesiscited by 41
  6. 2023Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignmentcited by 39
  7. 2022Fast Learning Radiance Fields by Shooting Much Fewer Rayscited by 38
  8. 2023Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matchingcited by 37
  9. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  10. 2024Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assemblycited by 35
  11. 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mappingcited by 27
  12. 2024UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusioncited by 23
33 more
  1. 2022HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfacescited by 22
  2. 2022Latent Partition Implicit with Surface Codes for 3D Representationcited by 21
  3. 2024Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mappingcited by 15
  4. 2025MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstructioncited by 15
  5. 2023GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Cloudscited by 11
  6. 2022Single-view 3D Mesh Reconstruction for Seen and Unseen Categoriescited by 10
  7. 2022Leveraging Single-View Images for Unsupervised 3D Point Cloud Completioncited by 8
  8. 2023NAISR: A 3D Neural Additive Model for Interpretable Shape Representationcited by 7
  9. 2025Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformationcited by 7
  10. 2025GAP: Gaussianize Any Point Clouds with Text Guidancecited by 7
  11. 2023Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentationcited by 6
  12. 2023BuilDiff: 3D Building Shape Generation using Single-Image Conditional Point Cloud Diffusion Modelscited by 6
  13. 2025U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matchingcited by 3
  14. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  15. 20243D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapescited by 2
  16. 2022CD2: Fine-grained 3D Mesh Reconstruction With Twice Chamfer Distancecited by 1
  17. 2023P2CADNet: An End-to-End Reconstruction Network for Parametric 3D CAD Model from Point Cloudscited by 1
  18. 2024DiffPoint: Single and Multi-view Point Cloud Reconstruction with ViT Based Diffusion Modelcited by 1
  19. 2025MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Imagecited by 1
  20. 2023Deep Learning Framework for Spleen Volume Estimation from 2D Cross-sectional Viewscited by 0
  21. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
  22. 2023GMTR: Graph Matching Transformerscited by 0
  23. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  24. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  25. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  26. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  27. 2024Shape2.5D: A Dataset of Texture-less Surfaces for Depth and Normals Estimationcited by 0
  28. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0
  29. 2024Towards General Deepfake Detection with Dynamic Curriculumcited by 0
  30. 2024Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphscited by 0
  31. 2025Mask6D: Masked Pose Priors For 6D Object Pose Estimationcited by 0
  32. 2026MetaSSP: Enhancing Semi-supervised Implicit 3D Reconstruction through Meta-adaptive EMA and SDF-aware Pseudo-label Evaluationcited by 0
  33. 2026Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcitycited by 0