mlsanityData to 7 Oct 2026

Neural Implicit 3D Shapes from Single Images with Spatial Patterns

arXiv 2106.03087 ↗First posted 6 Jun 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural implicit functions have achieved impressive results for reconstructing 3D shapes from single images. However, the image features for describing 3D point samplings of implicit functions are less effective when significant variations of occlusions, views, and appearances exist from the image. To better encode image features, we study a geometry-aware convolutional kernel to leverage geometric relationships of point samplings by the proposed spatial pattern, i.e., a structured point set. Specifically, the kernel operates at 2D projections of 3D points from the spatial pattern. Supported by the spatial pattern, the 2D kernel encodes geometric information that is crucial for 3D reconstruction tasks, while traditional ones mainly consider appearance information. Furthermore, to enable the network to discover more adaptive spatial patterns for further capturing non-local contextual information, the kernel is devised to be deformable manipulated by a spatial pattern generator. Experimental results on both synthetic and real datasets demonstrate the superiority of the proposed method. Pre-trained models, codes, and data are available at https://github.com/yixin26/SVR-SP.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 42 references that are in the map. First posted on arXiv 6 Jun 2021.

Builds on

36 of 42 references.

References · 36

  1. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  3. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  5. 2017Deformable Convolutional Networkscited by 1,481
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  9. 2020Neural Sparse Voxel Fieldscited by 959
  10. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  11. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  12. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
24 more
  1. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  2. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  3. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  4. 2017Neural 3D Mesh Renderercited by 437
  5. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  6. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  7. 2019Pay Less Attention with Lightweight and Dynamic Convolutionscited by 211
  8. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  9. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  10. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  11. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  12. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  13. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  14. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 118
  15. 2016Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervisioncited by 106
  16. 2018Unsupervised Learning of Shape and Pose with Differentiable Point Cloudscited by 89
  17. 2018Learning Shape Priors for Single-View 3D Completion and Reconstructioncited by 68
  18. 20193DN: 3D Deformation Networkcited by 60
  19. 2018Im2Struct: Recovering 3D Shape Structure from a Single RGB Imagecited by 55
  20. 2020D2IM-Net: Learning Detail Disentangled Implicit Fields from Single Imagescited by 42
  21. 20183D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Imagecited by 40
  22. 2019A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Imagescited by 37
  23. 2019Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstructioncited by 28
  24. 2020Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetrycited by 24

Built on by

Not cited yet.