mlsanityData to 7 Oct 2026

Curriculum DeepSDF

arXiv 2003.08593 ↗First posted 19 Mar 2020cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

When learning to sketch, beginners start with simple and flexible shapes, and then gradually strive for more complex and accurate ones in the subsequent training sessions. In this paper, we design a "shape curriculum" for learning continuous Signed Distance Function (SDF) on shapes, namely Curriculum DeepSDF. Inspired by how humans learn, Curriculum DeepSDF organizes the learning task in ascending order of difficulty according to the following two criteria: surface accuracy and sample difficulty. The former considers stringency in supervising with ground truth, while the latter regards the weights of hard training samples near complex geometry and fine structure. More specifically, Curriculum DeepSDF learns to reconstruct coarse shapes at first, and then gradually increases the accuracy and focuses more on complex local details. Experimental results show that a carefully-designed curriculum leads to significantly better shape reconstructions with the same training data, training epochs and network architecture as DeepSDF. We believe that the application of shape curricula can benefit the training process of a wide variety of 3D shape representation learning methods.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 19; 2023: 14; 2024: 7; 2025: 3; 2026: 2.

62 papers.

Sort:

By area:

  1. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  2. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  3. 2021Advances in Neural Renderingcited by 365
  4. 2021Curriculum Learning: A Surveycited by 257
  5. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  6. 2022Curriculum Temperature for Knowledge Distillationcited by 110
  7. 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
  8. 2023Curricular Contrastive Regularization for Physics-aware Single Image Dehazingcited by 83
  9. 2021MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networkscited by 75
  10. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  11. 2023NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functionscited by 65
  12. 2024Advances in 3D Generation: A Surveycited by 62
38 more
  1. 2023Urban Radiance Field Representation with Deformable Neural Mesh Primitivescited by 55
  2. 2023NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenescited by 53
  3. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 46
  4. 2022GIFS: Neural Implicit Function for General Shape Representationcited by 45
  5. 2022Surface Reconstruction from Point Clouds: A Survey and a Benchmarkcited by 41
  6. 2022DrapeNet: Garment Generation and Self-Supervised Drapingcited by 39
  7. 2021Phase Transitions, Distance Functions, and Implicit Neural Representationscited by 38
  8. 2022Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flowcited by 38
  9. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  10. 2021Multiresolution Deep Implicit Functions for 3D Shape Representationcited by 35
  11. 2023LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDARcited by 31
  12. 2022SPAMs: Structured Implicit Parametric Modelscited by 29
  13. 20223PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologiescited by 27
  14. 2022Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Spacecited by 22
  15. 2023CL-MAE: Curriculum-Learned Masked Autoencoderscited by 21
  16. 2022PRIF: Primary Ray-based Implicit Functioncited by 17
  17. 2023RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereocited by 15
  18. 2023MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Drivingcited by 11
  19. 2024MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Stepcited by 11
  20. 2024DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scalingcited by 9
  21. 2024Zero-Shot Multi-Object Scene Completioncited by 9
  22. 2023Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Modelscited by 8
  23. 2022NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representationcited by 7
  24. 2025Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformationcited by 7
  25. 2021LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodiescited by 6
  26. 2022DeepMend: Learning Occupancy Functions to Represent Shape for Repaircited by 6
  27. 2022DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repaircited by 5
  28. 2021Implicit Neural Deformation for Sparse-View Face Reconstructioncited by 4
  29. 2021UNIST: Unpaired Neural Implicit Shape Translation Networkcited by 4
  30. 2022NeuralMeshing: Differentiable Meshing of Implicit Neural Representationscited by 3
  31. 2023Semantic-Aware Implicit Template Learning via Part Deformation Consistencycited by 3
  32. 2023Implicit Modeling of Non-rigid Objects with Cross-Category Signalscited by 3
  33. 2021Towards Generalising Neural Implicit Representationscited by 2
  34. 2021Geometry encoding for numerical simulationscited by 2
  35. 2021Contrastive Object-level Pre-training with Spatial Noise Curriculum Learningcited by 2
  36. 2022Neural Structure Fields with Application to Crystal Structure Autoencoderscited by 2
  37. 2023A Comprehensive Study of Privacy Risks in Curriculum Learningcited by 2
  38. 2024Oriented-grid Encoder for 3D Implicit Representationscited by 2

50 most cited of 62 All 62 (JSON)