Pith. sign in

REVIEW 26 cited by

Implicit Geometric Regularization for Learning Shapes

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2002.10099 v2 pith:U2R2QNCG submitted 2020-02-24 cs.LG cs.CVcs.GRstat.ML

classification cs.LGcs.CVcs.GRstat.ML
keywords implicitneuralrepresentationslevelanalysisfidelitygeometricloss
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Representing shapes as level sets of neural networks has been recently proved to be useful for different shape analysis and reconstruction tasks. So far, such representations were computed using either: (i) pre-computed implicit shape representations; or (ii) loss functions explicitly defined over the neural level sets. In this paper we offer a new paradigm for computing high fidelity implicit neural representations directly from raw data (i.e., point clouds, with or without normal information). We observe that a rather simple loss function, encouraging the neural network to vanish on the input point cloud and to have a unit norm gradient, possesses an implicit geometric regularization property that favors smooth and natural zero level set surfaces, avoiding bad zero-loss solutions. We provide a theoretical analysis of this property for the linear case, and show that, in practice, our method leads to state of the art implicit neural representations with higher level-of-details and fidelity compared to previous methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 26 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Points as Tori: Fast Pointwise Signed Distance for Point Clouds

    cs.GR 2026-07 conditional novelty 7.0 of 10

    Blending closed-form torus SDFs, with per-point coefficients predicted by a shared neural network, yields pointwise signed distance to point clouds without explicit reconstruction.

  2. Geometry Field Splatting with Gaussian Surfels

    cs.GR 2024-11 conditional novelty 7.0 of 10

    Gaussian surfels can parameterize a stochastic geometry field with a closed-form, near-exact differentiable splatting renderer, improving 3D surface reconstruction on DTU and BlendedMVS.

  3. Masked Topology Modeling for Self-Supervised Learning on Parametric CAD

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Masked Topology Modeling pretrains B-rep encoders by hiding face-adjacency edges and predicting their kernel-computed convexity and curve type, improving label efficiency on CAD benchmarks.

  4. Hydrodynamic Effects in Cryogenic Buffer Gas Cells: Design Insights from Hybrid Simulations

    quant-ph 2025-08 unverdicted novelty 6.0 of 10

    In a spherical cryogenic buffer gas cell, vortices form at certain helium flows and injection angles and can enhance molecule extraction, which should be visible in beam velocity or time-of-flight measurements.

  5. Mechanics Simulation with Implicit Neural Representations of Complex Geometries

    cs.CE 2025-07 conditional novelty 6.0 of 10

    A framework that uses neural implicit geometry representations to feed shifted-boundary finite element simulations, removing explicit surface meshing for linear elasticity on complex shapes.

  6. ViscoReg: Neural Signed Distance Functions via Viscosity Solutions

    cs.GR 2025-07 conditional novelty 6.0 of 10

    A viscosity-regularized Eikonal loss with annealed epsilon improves Neural SDF reconstruction and yields the first generalization bound for SDF learning.

  7. NOVA3D: Normal Aligned Video Diffusion Model for Single Image to 3D Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A video diffusion model fine-tuned to output both color and normal maps, aligned by a geometry-temporal attention block, reconstructs textured 3D meshes from a single image.

  8. Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space

    cs.CV 2025-04 conditional novelty 6.0 of 10

    Common3D learns deformable 3D morphable models for common objects from object-centric videos using neural features, and solves pose, segmentation, and semantic correspondence in a self-supervised, zero-shot manner.

  9. Creating Your Editable 3D Photorealistic Avatar with Tetrahedron-constrained Gaussian Splatting

    cs.GR 2025-04 conditional novelty 6.0 of 10

    TetGS is a hybrid representation that embeds Gaussian kernels inside tetrahedral grids, enabling locally controlled geometric and appearance edits of 3D avatars reconstructed from monocular video.

  10. Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video

    cs.CV 2025-04 conditional novelty 6.0 of 10

    A NeRF-based system estimates camera motion as continuous velocities and recovers accurate camera poses and scene geometry from monocular video without depth priors.

  11. Few-Shot Multi-Human Neural Rendering Using Geometry Constraints

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A neural implicit method uses SMPL body meshes as geometric priors to reconstruct and re-render multi-human scenes from 5 to 20 input views.

  12. Robustifying Fourier Features Embeddings for Implicit Neural Representations

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A bias-free MLP filter applied multiplicatively to Fourier features, with a line-search learning-rate controller, reduces noise and improves implicit neural representation fitting across images, shapes, and NeRF.

  13. Sparis: Neural Implicit Surface Reconstruction of Indoor Scenes from Sparse Views

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Inter-image feature matching, not monocular depth, supplies the depth prior that enables accurate neural implicit surface reconstruction from sparse indoor views.

  14. DGNS: Deformable Gaussian Splatting and Dynamic Neural Surface for Monocular Dynamic 3D Reconstruction

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A hybrid of deformable Gaussian splatting and dynamic neural SDF achieves state-of-the-art 3D mesh accuracy from monocular video while keeping view synthesis competitive.

  15. Neural 4D Evolution under Large Topological Changes from 2D Images

    cs.CV 2024-11 conditional novelty 6.0 of 10

    N4DE learns 4D deformations with large topology changes from 2D images by evolving a time-conditioned neural SDF with hash grids and implicit Gaussian splatting.

  16. Robust SG-NeRF: Robust Scene Graph Aided Neural Surface Reconstruction

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A pose-confidence method using a detached view-direction-free color network, Monte Carlo re-localization, and dynamic scene graph updates improves neural surface reconstruction under outlier camera poses.

  17. Spacecraft Safe Robust Control Using Implicit Neural Representation for Geometrically Complex Targets in Proximity Operations

    eess.SY 2025-07 reject novelty 5.0 of 10

    A two-layer robust controller uses a learned signed distance function with conservative error margins and circulation inequalities to keep a chaser spacecraft collision-free near complex-geometry targets.

  18. HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity

    cs.CV 2025-06 conditional novelty 5.0 of 10

    HiNeuS builds accurate 3D surfaces from photos by combining SDF-based visibility checks, local planar regularization, and rendering-error-weighted Eikonal constraints, reporting SOTA on several benchmarks.

  19. 3D Surface Reconstruction with Enhanced High-Frequency Details

    cs.CV 2025-05 conditional novelty 5.0 of 10

    FreNeuS adds gradient-guided ray sampling and high-frequency-weighted color loss to NeuS, reducing mean Chamfer distance from 0.84 to 0.73 on DTU and from 1.97 to 1.11 on six NeRF-synthetic scenes.

  20. Spatially-Adaptive Hash Encodings For Neural Surface Reconstruction

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A learned spatial mask modulates multi-resolution hash grid features per scene location, improving neural surface reconstruction accuracy on DTU and Tanks and Temples.

  21. HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition

    cs.CV 2024-11 conditional novelty 5.0 of 10

    A heat-equation-based loss for neural signed distance functions gives an asymptotically sufficient condition for convergence to the true distance, with better surface and distance accuracy on shape benchmarks.

  22. Neural shape reconstruction from multiple views with static pattern projection

    cs.CV 2025-06 conditional novelty 4.0 of 10

    A neural signed-distance field is jointly optimized with camera and projector poses to fuse structured-light images captured from freely moving devices.

  23. SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splatting

    cs.CV 2025-05 conditional novelty 4.0 of 10

    A feed-forward model regressing 2D Gaussian splat parameters from three views reports the best Chamfer distance on DTU sparse reconstruction in its comparison table, and competitive novel view synthesis, at roughly 80...

  24. NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Clouds

    cs.CV 2024-11 conditional novelty 4.0 of 10

    NumGrad-Pull uses tri-plane feature grids, numerical gradients, progressive resolution increases, and complementary sampling to improve signed-distance-function surface reconstruction from point clouds.

  25. $\text{S}^{3}$Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Model

    cs.CV 2024-11 reject novelty 4.0 of 10

    S3Mamba applies scale-modulated state space models to arbitrary-scale super-resolution, reporting marginal PSNR gains over prior INR-based methods.

  26. STITCH: Surface reconstrucTion using Implicit neural representations with Topology Constraints and persistent Homology

    cs.CV 2024-12 reject novelty 3.0 of 10

    STITCH augments Neural-Pull with a topological loss derived from persistent homology to encourage a single connected component in reconstructed surfaces.

Pith tools