mlsanityData to 7 Oct 2026

ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction

arXiv 2212.04096 ↗First posted 8 Dec 2022cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

This work introduces alternating latent topologies (ALTO) for high-fidelity reconstruction of implicit 3D surfaces from noisy point clouds. Previous work identifies that the spatial arrangement of latent encodings is important to recover detail. One school of thought is to encode a latent vector for each point (point latents). Another school of thought is to project point latents into a grid (grid latents) which could be a voxel grid or triplane grid. Each school of thought has tradeoffs. Grid latents are coarse and lose high-frequency detail. In contrast, point latents preserve detail. However, point latents are more difficult to decode into a surface, and quality and runtime suffer. In this paper, we propose ALTO to sequentially alternate between geometric representations, before converging to an easy-to-decode latent. We find that this preserves spatial expressiveness and makes decoding lightweight. We validate ALTO on implicit 3D recovery and observe not only a performance improvement over the state-of-the-art, but a runtime improvement of 3-10×. Project website at https://visual.ee.ucla.edu/alto.htm/.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 70 of its 91 references that are in the map. First posted on arXiv 8 Dec 2022.

Builds on

70 of 91 references.

References · 70

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  9. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  10. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  11. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  12. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
38 more
  1. 2020Point Transformercited by 1,462
  2. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  3. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  4. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  5. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  6. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  7. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  8. 2020Convolutional Occupancy Networkscited by 760
  9. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  10. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  11. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  12. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  13. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  14. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  15. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  16. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  17. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  18. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  19. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  20. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  21. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  22. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  23. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  24. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  25. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
  26. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  27. 2017Learning a Multi-View Stereo Machinecited by 194
  28. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  29. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  30. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  31. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  32. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  33. 20163D Shape Induction from 2D Views of Multiple Objectscited by 121
  34. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  35. 2021Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representationscited by 107
  36. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
  37. 2020Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinementcited by 105
  38. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 92

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 12; 2025: 3; 2026: 1.

21 papers.

Sort:

By area:

  1. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
  2. 2024SpatialTracker: Tracking Any 2D Pixels in 3D Spacecited by 178
  3. 20244K4DGen: Panoramic 4D Generation at 4K Resolutioncited by 54
  4. 2024SemCity: Semantic Scene Generation with Triplane Diffusioncited by 53
  5. 2024Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mappingcited by 15
  6. 2024EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encodingcited by 13
  7. 2023Pushing the Limits of 3D Shape Generation at Scalecited by 11
  8. 2025SliceOcc: Indoor 3D Semantic Occupancy Prediction with Vertical Slice Representationcited by 8
  9. 2023Ins-HOI: Instance Aware Human-Object Interactions Recoverycited by 7
  10. 2024GridFormer: Point-Grid Transformer for Surface Reconstructioncited by 7
  11. 2024Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Cloudscited by 7
  12. 2024Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priorscited by 7
9 more
  1. 2023Learning Any-View 6DoF Robotic Grasping in Cluttered Scenes via Neural Surface Renderingcited by 5
  2. 2024Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Cloudscited by 5
  3. 2024PointDreamer: Zero-shot 3D Textured Mesh Reconstruction from Colored Point Cloudcited by 3
  4. 2025NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serializationcited by 3
  5. 2024Sharpening Neural Implicit Functions with Frequency Consolidation Priorscited by 2
  6. 2026Reconstructing Building Height from Spaceborne TomoSAR Point Clouds Using a Dual-Topology Networkcited by 2
  7. 2024DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstructioncited by 1
  8. 2023Polyhedral Surface: Self-supervised Point Cloud Reconstruction Based on Polyhedral Surfacecited by 0
  9. 2025SurfR: Surface Reconstruction with Multi-scale Attentioncited by 0