mlsanityData to 14 Oct 2026

Neural Poisson: Indicator Functions for Neural Fields

arXiv 2211.14249 ↗First posted 25 Nov 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Implicit neural field generating signed distance field representations (SDFs) of 3D shapes have shown remarkable progress in 3D shape reconstruction and generation. We introduce a new paradigm for neural field representations of 3D scenes; rather than characterizing surfaces as SDFs, we propose a Poisson-inspired characterization for surfaces as indicator functions optimized by neural fields. Crucially, for reconstruction of real scan data, the indicator function representation enables simple and effective constraints based on common range sensing inputs, which indicate empty space based on line of sight. Such empty space information is intrinsic to the scanning process, and incorporating this knowledge enables more accurate surface reconstruction. We show that our approach demonstrates state-of-the-art reconstruction performance on both synthetic and real scanned 3D scene data, with 9.5% improvement in Chamfer distance over state of the art.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 16 of its 34 references that are in the map. First posted on arXiv 25 Nov 2022.

Builds on

16 of 34 references.

References · 16

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  4. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  5. 2021Neural Fields in Visual Computing and Beyondcited by 540
  6. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  7. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  8. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 380
  9. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  10. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  11. 2016BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integrationcited by 116
  12. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
4 more
  1. 2021NPMs: Neural Parametric Models for 3D Deformable Shapescited by 90
  2. 2019SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scanscited by 77
  3. 2020Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representationscited by 39
  4. 2022SPAMs: Structured Implicit Parametric Modelscited by 29

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 0; 2026: 1.

7 papers.

  1. 2023Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignmentcited by 39
  2. 2023Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priorscited by 28
  3. 2023GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Cloudscited by 11
  4. 2024HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Conditioncited by 8
  5. 2024Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priorscited by 7
  6. 2024AiSDF: Structure-aware Neural Signed Distance Fields in Indoor Scenescited by 0
  7. 2026Surface Reconstruction from Range Scans Under Visibility Constraintscited by 0