← Back to all news
arXiv Machine Learning

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.

Related stories

arXiv Computer Vision
Sep 17

Generalizable Neural Reconstruction of High-Fidelity Surfaces via Sparse Volumetric Representations

The paper introduces SVRecon, a generalizable neural surface reconstruction framework that uses sparse volumetric representations to achieve high-resolution 3D reconstruction. It employs a two-stage architecture: first predicting occupied voxels with an occupancy network, then rendering only within those regions using specialized sparse algorithms. This approach allows reconstruction at resolutions up to 512³ on 32 GB hardware, producing smoother and more precise surfaces, especially in sparse-view scenarios.

By Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Ming Xu, Hieu Le, Pascal Fua
efficiency
More like this →
Hugging Face Trending Papers
Jul 21

Fluid-SDF: Ultra-Lightweight and Editable Implicit Shape Representation via Differentiable Primitives

Implicit Neural Representations (INRs) have become the standard for continuous 2D shape modeling, but they suffer from black-box uneditability, vulnerability to noise, and high parameter counts that severely hinder deployment on edge devices. We introduce Fluid-SDF, a highly compressed, differentiable Constructive Solid Geometry (CSG) framework that models shapes using explicit geometric primitives blended via a smooth minimum function.

More like this →
arXiv Computer Vision
Sep 4

P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing

P-CORE introduces a self‑supervised surface consistency technique for point‑based neural representations, enabling robust adaptation to large deformations without needing ground‑truth deformed images. By generating random deformations and enforcing that the predicted surface after deformation matches the deformation applied to the original surface prediction, the method leverages attention‑based point representations with a learned interpolation kernel. Experiments on synthetic benchmarks and real‑world datasets show improved zero‑shot editing performance and reduced artifacts compared to existing point‑based approaches.

By Yanshu Zhang, Shichong Peng, Mehran Aghabozorgi, Alireza Moazeni, Ke Li
benchmarks
More like this →
arXiv Computer Vision
Sep 7

Compact Neural Appearance Models for Efficient Gaussian Splatting

The paper introduces a compact neural appearance model for 3D Gaussian Splatting that replaces traditional low‑order spherical harmonics (SH) with a tiny shared MLP decoding per‑primitive latent codes. It compares SH with recent spherical appearance models, integrating all into a unified CUDA rasterizer and WebGL viewer, and demonstrates that the new neural representation reduces per‑primitive appearance storage from 192 to 28 bytes, speeds optimization by 1.3×, and improves reconstruction quality. The study also analyzes how different appearance parametrizations affect geometry recovery and the handling of non‑static scene content.

By Florian Hahlbohm, Jorge Condor, Linus Franke, Martin Eisemann, Marcus Magnor
More like this →