Pith. sign in

REVIEW 8 cited by

GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction

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 2403.16964 v2 pith:5K6XXS4J submitted 2024-03-25 cs.CV

classification cs.CV
keywords renderingneuralscenebenefitscomputercorefieldsgeometry
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Presenting a 3D scene from multiview images remains a core and long-standing challenge in computer vision and computer graphics. Two main requirements lie in rendering and reconstruction. Notably, SOTA rendering quality is usually achieved with neural volumetric rendering techniques, which rely on aggregated point/primitive-wise color and neglect the underlying scene geometry. Learning of neural implicit surfaces is sparked from the success of neural rendering. Current works either constrain the distribution of density fields or the shape of primitives, resulting in degraded rendering quality and flaws on the learned scene surfaces. The efficacy of such methods is limited by the inherent constraints of the chosen neural representation, which struggles to capture fine surface details, especially for larger, more intricate scenes. To address these issues, we introduce GSDF, a novel dual-branch architecture that combines the benefits of a flexible and efficient 3D Gaussian Splatting (3DGS) representation with neural Signed Distance Fields (SDF). The core idea is to leverage and enhance the strengths of each branch while alleviating their limitation through mutual guidance and joint supervision. We show on diverse scenes that our design unlocks the potential for more accurate and detailed surface reconstructions, and at the meantime benefits 3DGS rendering with structures that are more aligned with the underlying geometry.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. ReMoSPLAT: Reactive Mobile Manipulation Control on a Gaussian Splat

    cs.RO 2025-12 conditional novelty 6.0 of 10

    ReMoSPLAT achieves reactive mobile-manipulation collision avoidance by querying distances from a Gaussian Splat reconstruction, matching a ground-truth-SDF controller in simulation.

  2. GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A camera-only Gaussian-surfel pipeline reconstructs full Waymo scenes, converts them to binary occupancy labels, and trains CVT-Occ to generalize on Occ3D-Waymo and Occ3D-nuScenes at a level close to or above LiDAR-la...

  3. 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.

  4. Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering

    cs.CV 2025-10 conditional novelty 5.0 of 10

    UGSDF achieves state-of-the-art novel-view rendering of dynamic urban objects without LiDAR or 3D motion annotations by jointly optimizing SDFs and 3D Gaussians under 2D depth and point-tracking priors.

  5. 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...

  6. Impact of Solar Particle Events on Space Radiation Shielding: OLTARIS Simulation and Quantum Optimization of Material Selection using QAOA and VQE Algorithms

    physics.med-ph 2025-08 reject novelty 5.0 of 10

    The abstract claims quantum-optimized shielding material selection, but the full text is an unrelated 3D Gaussian Splatting paper, so the claim is unsupported.

  7. 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.

  8. 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.

Pith tools