REVIEW 15 cited by
Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
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
read the original abstract
Recently, 3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results, while allowing the rendering of high-resolution images in real-time. However, leveraging 3D Gaussians for surface reconstruction poses significant challenges due to the explicit and disconnected nature of 3D Gaussians. In this work, we present Gaussian Opacity Fields (GOF), a novel approach for efficient, high-quality, and adaptive surface reconstruction in unbounded scenes. Our GOF is derived from ray-tracing-based volume rendering of 3D Gaussians, enabling direct geometry extraction from 3D Gaussians by identifying its levelset, without resorting to Poisson reconstruction or TSDF fusion as in previous work. We approximate the surface normal of Gaussians as the normal of the ray-Gaussian intersection plane, enabling the application of regularization that significantly enhances geometry. Furthermore, we develop an efficient geometry extraction method utilizing Marching Tetrahedra, where the tetrahedral grids are induced from 3D Gaussians and thus adapt to the scene's complexity. Our evaluations reveal that GOF surpasses existing 3DGS-based methods in surface reconstruction and novel view synthesis. Further, it compares favorably to or even outperforms, neural implicit methods in both quality and speed.
Forward citations
Cited by 15 Pith papers
-
Points as Tori: Fast Pointwise Signed Distance for Point Clouds
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.
-
Beyond a Single Light: A Large-Scale Aerial Dataset for Urban Scene Reconstruction Under Varying Illumination
SkyLume contributes 10 real-world UAV urban regions captured at morning, noon, and afternoon with LiDAR-based ground truth, plus the Temporal Consistency Coefficient metric for cross-time albedo stability.
-
MVGBench: Comprehensive Benchmark for Multi-view Generation Models
MVGBench evaluates multi-view generators through self-consistency of 3D reconstructions and uses this protocol to rank 12 models and build a better one.
-
Manifold-GS: Certified Hybrid Assets via Varifold-Conservative Gaussian Splatting
Gaussian splat scenes can be exported as certified open patches with conservative mass transport, cutting collision-hallucination area versus watertight mesh baselines on three DTU scenes at lower coverage.
-
GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting
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...
-
A Mixed-Primitive-based Gaussian Splatting Method for Surface Reconstruction
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.
-
VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding
VoteSplat embeds per-Gaussian 3D offset vectors, supervises them with SAM mask centers, and clusters the resulting 3D votes to segment and localize objects in Gaussian Splatting scenes.
-
HuSc3D: Human Sculpture dataset for 3D object reconstruction
HuSc3D provides six real-world scenes of white, low-texture sculptures with varied capture conditions, and benchmarks show Gaussian-splatting methods clearly outperform NeRF-based methods.
-
Point Cloud Segmentation of Agricultural Vehicles using 3D Gaussian Splatting
Training point cloud segmentation models only on LiDAR data synthesized from 3D Gaussian Splatting meshes achieves around 91% mIoU on real agricultural vehicle scans.
-
Generating Synthetic Stereo Datasets using 3D Gaussian Splatting and Expert Knowledge Transfer
Using 3D Gaussian Splatting renderings with FoundationStereo pseudo-depth labels produces synthetic stereo training data that transfers to real-world zero-shot benchmarks as well as or better than prior NeRF-based methods.
-
Wavelet-GS: 3D Gaussian Splatting with Wavelet Decomposition
Wavelet-GS splits a 3D point cloud into low- and high-frequency wavelet parts, trains each with its own strategy, plus a relight module, reporting gains over prior 3DGS variants on four datasets.
-
LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling
LocalDyGS reconstructs dynamic scenes by decomposing space into seed-based local regions and generating time-varying Temporal Gaussians, though its claim of being first for large-scale scenes omits the existing Swift4...
-
RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS
RobustSplat improves transient-free 3D Gaussian Splatting by postponing densification to 10,000 iterations and bootstrapping mask supervision from low to high resolution.
-
FGO-SLAM: Enhancing Gaussian SLAM with Globally Consistent Opacity Radiance Field
FGO-SLAM combines feature-based global pose adjustment with a 3D Gaussian opacity field to improve tracking accuracy, mapping quality, and direct mesh extraction in Gaussian SLAM.
-
Multi-view Normal and Distance Guidance Gaussian Splatting for Surface Reconstruction
A 3DGS surface reconstruction method that enforces multi-view distance and normal consistency between nearby views to reduce geometry drift.
Discussion (0). Continue with ORCID to comment.