REVIEW 6 cited by
Voxurf: Voxel-based Efficient and Accurate Neural 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
read the original abstract
Neural surface reconstruction aims to reconstruct accurate 3D surfaces based on multi-view images. Previous methods based on neural volume rendering mostly train a fully implicit model with MLPs, which typically require hours of training for a single scene. Recent efforts explore the explicit volumetric representation to accelerate the optimization via memorizing significant information with learnable voxel grids. However, existing voxel-based methods often struggle in reconstructing fine-grained geometry, even when combined with an SDF-based volume rendering scheme. We reveal that this is because 1) the voxel grids tend to break the color-geometry dependency that facilitates fine-geometry learning, and 2) the under-constrained voxel grids lack spatial coherence and are vulnerable to local minima. In this work, we present Voxurf, a voxel-based surface reconstruction approach that is both efficient and accurate. Voxurf addresses the aforementioned issues via several key designs, including 1) a two-stage training procedure that attains a coherent coarse shape and recovers fine details successively, 2) a dual color network that maintains color-geometry dependency, and 3) a hierarchical geometry feature to encourage information propagation across voxels. Extensive experiments show that Voxurf achieves high efficiency and high quality at the same time. On the DTU benchmark, Voxurf achieves higher reconstruction quality with a 20x training speedup compared to previous fully implicit methods. Our code is available at https://github.com/wutong16/Voxurf.
Forward citations
Cited by 6 Pith papers
-
Geometry Field Splatting with Gaussian Surfels
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.
-
IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations
A diffusion model that decomposes arbitrary numbers of images of the same object, under varying lighting, into albedo, normal, metallic, and roughness maps with multi-view consistency.
-
GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction
GausSurf combines iterative patch-match MVS refinement with 3D Gaussian Splatting and normal priors, achieving state-of-the-art surface reconstruction at 7.2 minutes per DTU scene.
-
GSurf: Learning Signed Distance Fields from Splatting Opaque Gaussians for High-quality 3D Reconstruction
GSurf learns a signed distance field supervised by Gaussian splat centers and renders via splatting, yielding compact meshes faster than previous Gaussian-SDF hybrids.
-
Robust SG-NeRF: Robust Scene Graph Aided Neural Surface Reconstruction
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.
-
Disentangled Geometry and Appearance for Efficient Multi-View Surface Reconstruction and Rendering
A disentangled geometry-and-appearance model over explicit meshes with differentiable rasterization achieves fast training and rendering for multi-view reconstruction.
Discussion (0). Continue with ORCID to comment.