Pith. sign in

REVIEW 15 cited by

NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2312.00846 v2 pith:5EANSN5V submitted 2023-12-01 cs.CV

Hanlin Chen , Chen Li , Yunsong Wang , Gim Hee Lee This is my paper
classification cs.CV
keywords splattingsurfacegaussianreconstructionimplicitneuralguidancepoint
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Existing neural implicit surface reconstruction methods have achieved impressive performance in multi-view 3D reconstruction by leveraging explicit geometry priors such as depth maps or point clouds as regularization. However, the reconstruction results still lack fine details because of the over-smoothed depth map or sparse point cloud. In this work, we propose a neural implicit surface reconstruction pipeline with guidance from 3D Gaussian Splatting to recover highly detailed surfaces. The advantage of 3D Gaussian Splatting is that it can generate dense point clouds with detailed structure. Nonetheless, a naive adoption of 3D Gaussian Splatting can fail since the generated points are the centers of 3D Gaussians that do not necessarily lie on the surface. We thus introduce a scale regularizer to pull the centers close to the surface by enforcing the 3D Gaussians to be extremely thin. Moreover, we propose to refine the point cloud from 3D Gaussians Splatting with the normal priors from the surface predicted by neural implicit models instead of using a fixed set of points as guidance. Consequently, the quality of surface reconstruction improves from the guidance of the more accurate 3D Gaussian splatting. By jointly optimizing the 3D Gaussian Splatting and the neural implicit model, our approach benefits from both representations and generates complete surfaces with intricate details. Experiments on Tanks and Temples verify the effectiveness of our proposed method.

Discussion (0). Sign in to comment.

Forward citations

Cited by 15 Pith papers

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

  1. 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.

  2. HoloTetSphere: Unified TetSphere Mesh Reconstruction for Physical Simulations

    cs.GR 2026-07 conditional novelty 6.0 of 10

    Coupling tetrahedra to Gaussians and pruning via a vertex-shared continuous opacity field produces unified, single-component tetrahedral meshes suitable for FEM from multi-view images.

  3. Gaussian Splatting with Discretized SDF for Relightable Assets

    cs.GR 2025-07 conditional novelty 6.0 of 10

    A per-Gaussian discretized SDF with a projection-based consistency loss improves decomposition quality and relighting in Gaussian splatting, beating Gaussian-based baselines while using less memory.

  4. SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SurfaceSplat combines SDF-based coarse meshes with Gaussian splatting to improve sparse-view reconstruction and rendering, but the ablations do not isolate the effect of each component.

  5. A Mixed-Primitive-based Gaussian Splatting Method for Surface Reconstruction

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MP-GS combines Gaussian ellipses, line segments, and triangles as splatting primitives and reports state-of-the-art Chamfer distance on DTU and F1 on Tanks and Temples.

  6. Virtual Memory for 3D Gaussian Splatting

    cs.GR 2025-06 conditional novelty 6.0 of 10

    A proxy-mesh visibility buffer with page streaming and level of detail lets 3D Gaussian Splatting render scenes larger than GPU memory while culling occluded Gaussians.

  7. SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splatting

    cs.CV 2025-12 conditional novelty 5.0 of 10

    SurfFill completes missing thin structures in LiDAR point clouds by focusing Gaussian surfel splatting on density-ambiguous regions surrounding the gaps.

  8. Effective Gaussian Management for High-fidelity Scene Reconstruction

    cs.CV 2025-09 conditional novelty 5.0 of 10

    A Gaussian management framework with conflict-aware attribute decoupling, adaptive spherical-harmonic orders, and confidence-based SDF normal distillation improves appearance quality while cutting model size, at rough...

  9. SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies

    cs.CV 2025-08 conditional novelty 5.0 of 10

    A neural surface reconstruction method that applies multi-view feature consistency along the whole ray and an uncertainty-gated depth prior to improve sparse-view 3D reconstruction quality.

  10. CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting

    cs.CV 2025-07 conditional novelty 5.0 of 10

    CRUISE reconstructs real V2X driving scenes as editable Gaussians, then shows that training on its generated data improves 3D detection and tracking on the V2X-Seq benchmark.

  11. HRGS: Hierarchical Gaussian Splatting for Memory-Efficient High-Resolution 3D Reconstruction

    cs.CV 2025-06 conditional novelty 5.0 of 10

    HRGS reconstructs high-resolution 3D scenes by training a coarse global Gaussian model at low resolution, then refining small scene blocks in parallel while pruning low-importance Gaussians, achieving lower memory use...

  12. GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A 2D Gaussian Splatting method that uses foundation-model depth/normal priors plus deferred shading to improve reconstruction and relighting of reflective objects.

  13. Hybrid Mesh-Gaussian Representation for Efficient Indoor Scene Reconstruction

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A hybrid representation routes texture-rich flat indoor regions to a textured mesh and keeps Gaussians only for complex geometry, reducing Gaussian counts by 18-50% with roughly comparable rendering quality.

  14. ErpGS: Equirectangular Image Rendering enhanced with 3D Gaussian Regularization

    cs.CV 2025-05 conditional novelty 5.0 of 10

    ErpGS improves omnidirectional 3D Gaussian Splatting with geometric, scale, and distortion-aware regularizations plus a viewpoint-dependent mask, beating prior methods on public benchmarks.

  15. Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen

    cs.LG 2025-05 conditional novelty 4.0 of 10

    Crash prediction should learn from near-miss events and synthetic counterfactual scenarios, not just recorded crashes.

Pith tools