mlsanityData to 7 Oct 2026

Hierarchical Surface Prediction for 3D Object Reconstruction

arXiv 1704.00710 ↗First posted 3 Apr 2017cs.CVcited by 89

Not on the map. Why?

Abstract (arXiv)

Recently, Convolutional Neural Networks have shown promising results for 3D geometry prediction. They can make predictions from very little input data such as a single color image. A major limitation of such approaches is that they only predict a coarse resolution voxel grid, which does not capture the surface of the objects well. We propose a general framework, called hierarchical surface prediction (HSP), which facilitates prediction of high resolution voxel grids. The main insight is that it is sufficient to predict high resolution voxels around the predicted surfaces. The exterior and interior of the objects can be represented with coarse resolution voxels. Our approach is not dependent on a specific input type. We show results for geometry prediction from color images, depth images and shape completion from partial voxel grids. Our analysis shows that our high resolution predictions are more accurate than low resolution predictions.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 27; 2022: 24; 2023: 25; 2024: 8; 2025: 3; 2026: 2.

89 papers.

Sort:

By area:

  1. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  2. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  3. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  4. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  5. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  6. 2023Neural Kernel Surface Reconstructioncited by 102
  7. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  8. 2022CHORE: Contact, Human and Object REconstruction from a single RGB imagecited by 95
  9. 2022POCO: Point Convolution for Surface Reconstructioncited by 91
  10. 2021H3D-Net: Few-Shot High-Fidelity 3D Head Reconstructioncited by 81
  11. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  12. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
38 more
  1. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  2. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  3. 2021Neural Marching Cubescited by 50
  4. 20213D Shape Generation with Grid-based Implicit Functionscited by 48
  5. 2023OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queriescited by 48
  6. 2022GIFS: Neural Implicit Function for General Shape Representationcited by 45
  7. 2021Learning Generative Models of Textured 3D Meshes from Real-World Imagescited by 44
  8. 2021Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequencescited by 38
  9. 2023Point-Cloud Completion with Pretrained Text-to-image Diffusion Modelscited by 37
  10. 2022Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshescited by 34
  11. 2021Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstructioncited by 31
  12. 2022Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversioncited by 30
  13. 2023Gaussian Splatting with NeRF-based Color and Opacitycited by 30
  14. 2021RetrievalFuse: Neural 3D Scene Reconstruction with a Databasecited by 28
  15. 2022SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminatorscited by 26
  16. 2022Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstructioncited by 26
  17. 2021OctField: Hierarchical Implicit Functions for 3D Modelingcited by 25
  18. 2022Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Imagescited by 21
  19. 2022ALTO: Alternating Latent Topologies for Implicit 3D Reconstructioncited by 21
  20. 20213DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfacescited by 17
  21. 2021NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Droppingcited by 16
  22. 2023Neural Vector Fields: Implicit Representation by Explicit Learningcited by 16
  23. 2021StrobeNet: Category-Level Multiview Reconstruction of Articulated Objectscited by 14
  24. 2021NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mappingcited by 14
  25. 2022Primitive-based Shape Abstraction via Nonparametric Bayesian Inferencecited by 14
  26. 2023Deep Learning for Visual Localization and Mapping: A Surveycited by 14
  27. 2021AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representationscited by 13
  28. 2023ShaDDR: Interactive Example-Based Geometry and Texture Generation via 3D Shape Detailization and Differentiable Renderingcited by 13
  29. 2022Points2NeRF: Generating Neural Radiance Fields from 3D point cloudcited by 11
  30. 2023DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Imagecited by 11
  31. 2023Neural radiance fields in the industrial and robotics domain: applications, research opportunities and use casescited by 10
  32. 2024Pixel to Elevation: Learning to Predict Elevation Maps at Long Range using Images for Autonomous Offroad Navigationcited by 10
  33. 2026LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtentscited by 10
  34. 2023SCoDA: Domain Adaptive Shape Completion for Real Scanscited by 9
  35. 2024Planner3D: LLM-enhanced graph prior meets 3D indoor scene explicit regularizationcited by 9
  36. 2023Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstructioncited by 8
  37. 2021LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representationcited by 7
  38. 2021What's Behind the Couch? Directed Ray Distance Functions (DRDF) for 3D Scene Reconstructioncited by 7

50 most cited of 89 All 89 (JSON)