Pith. sign in

REVIEW 8 cited by

VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface 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 2406.05774 v2 pith:XIJSRX37 submitted 2024-06-09 cs.CV

classification cs.CV
keywords normalgeometricsurfaceparametersreconstructionacrossdepth-normalgaussian
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Although 3D Gaussian Splatting has been widely studied because of its realistic and efficient novel-view synthesis, it is still challenging to extract a high-quality surface from the point-based representation. Previous works improve the surface by incorporating geometric priors from the off-the-shelf normal estimator. However, there are two main limitations: 1) Supervising normals rendered from 3D Gaussians effectively updates the rotation parameter but is less effective for other geometric parameters; 2) The inconsistency of predicted normal maps across multiple views may lead to severe reconstruction artifacts. In this paper, we propose a Depth-Normal regularizer that directly couples normal with other geometric parameters, leading to full updates of the geometric parameters from normal regularization. We further propose a confidence term to mitigate inconsistencies of normal predictions across multiple views. Moreover, we also introduce a densification and splitting strategy to regularize the size and distribution of 3D Gaussians for more accurate surface modeling. Compared with Gaussian-based baselines, experiments show that our approach obtains better reconstruction quality and maintains competitive appearance quality at faster training speed and 100+ FPS rendering.

Discussion (0). Continue with ORCID 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. ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration

    cs.CV 2025-04 conditional novelty 6.0 of 10

    ToF-Splatting is the first 3D Gaussian Splatting SLAM system designed for sparse ToF depth, using a retrained multi-frame depth integration module with monocular cues and outlier filtering.

  2. GauSTAR: Gaussian Surface Tracking and Reconstruction

    cs.CV 2025-01 conditional novelty 6.0 of 10

    A Gaussian-on-mesh representation with adaptive unbinding and re-meshing achieves best-on-reported-sequences dynamic surface reconstruction, rendering, and tracking under topology changes.

  3. ChatSplat: 3D Conversational Gaussian Splatting

    cs.CV 2024-12 conditional novelty 6.0 of 10

    ChatSplat learns a 3D conversational field in Gaussian Splatting that supports object-, view-, and scene-level chat with an LLM at real-time speeds.

  4. AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for Indoor Room Reconstruction Using Smartphones

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Adaptive filtering of noisy phone depth and monocular normal priors improves Gaussian splatting based 3D indoor reconstruction and mesh extraction.

  5. GSurf: Learning Signed Distance Fields from Splatting Opaque Gaussians for High-quality 3D Reconstruction

    cs.CV 2024-11 conditional novelty 6.0 of 10

    GSurf learns a signed distance field supervised by Gaussian splat centers and renders via splatting, yielding compact meshes faster than previous Gaussian-SDF hybrids.

  6. 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.

  7. FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistency

    cs.CV 2025-01 conditional novelty 5.0 of 10

    FatesGS combines local monocular depth ranking, depth smoothing, and multi-view feature alignment in a 2D Gaussian splatting pipeline to obtain accurate surface meshes from only three views without dataset-scale pre-training.

  8. GLS: Geometry-aware 3D Language Gaussian Splatting

    cs.CV 2024-11 conditional novelty 5.0 of 10

    GLS jointly optimizes 3D Gaussian surface reconstruction and open-vocabulary segmentation, reporting improved accuracy on MuSHRoom, ScanNet++ and LERF-OVS.

Pith tools