arXiv Computer Vision
MicroSDF: Microfacet-Driven Hybrid Neural SDFs for Mixed-Reflectance Surface Reconstruction
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
5d ago
MicroSDF: Microfacet-Driven Hybrid Neural SDFs for Mixed-Reflectance Surface Reconstruction
Accurate 3D reconstruction in real-world environments remains a significant challenge due to the coexistence of reflective and non-reflective surfaces, which pose distinct modeling demands. Existing m...
arXiv Computer Vision
Sep 1
Gaussian-Voxel Duet: A Dual-Scaffolding Hybrid Representation for Fast and Accurate Monocular Surface Reconstruction
arXiv:2605.26616v2 Announce Type: replace Abstract: While 3D Gaussian Splatting has achieved remarkable success in photorealistic novel view synthesis, its pursuit of fast and high-fidelity 3D recons...
arXiv Computer Vision
Oct 1
DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions
arXiv:2605.10360v3 Announce Type: replace Abstract: While novel view synthesis (NVS) for dynamic scenes has seen significant progress, reconstructing temporally consistent geometric surfaces remains...
arXiv Machine Learning
Sep 25
M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals
M-plicits introduces a multiscale framework for neural implicit surfaces that models a surface as a residual sum of MLPs trained on nested neighborhoods. By localizing supervision to narrow bands around previous zero-level sets, the method achieves robustness to noisy input, avoids costly mesh extraction, and enables a multiscale sphere-tracing algorithm with analytical normal computation. Experiments on Stanford and Thingi32 show superior Chamfer distance and IoU metrics compared to existing methods while using far fewer parameters.
arXiv Computer Vision
Sep 30
NRF-GS: Neural Residual Fields for Expressive and Compact Gaussian Splatting
arXiv:2609.37115v1 Announce Type: new Abstract: We revisit the role of appearance modeling in 3D Gaussian Splatting (3DGS) and show that limited expressiveness in view-dependent reflectance is a key...
arXiv Computer Vision
Aug 28
NeuDonatello: Uncertainty-Aware Framework for Accurate Neural SDF Learning
NeuDonatello is a new framework for neural signed distance function (SDF) learning that explicitly models spatially varying uncertainty using Monte Carlo sampling. By incorporating this uncertainty into an adaptive regularization scheme and an uncertainty-aware SDF-to-density conversion, the method selectively strengthens geometric constraints where RGB supervision is unreliable, thereby improving surface reconstruction accuracy. Experiments show that NeuDonatello achieves state‑of‑the‑art results on diverse scenes using only posed RGB images.