arXiv Computer Vision September 17, 2026 By Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Ming Xu, Hieu Le, Pascal Fua

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

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

efficiency

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...

By Zhenhua Du, Zhen Tan, Haoyu Zhang, Dewen Hu, Shuaifeng Zhi, Peidong Liu

benchmarks

arXiv Machine Learning

Jun 25

SparseGS: Sparse View Synthesis using 3D Gaussian Splatting

arXiv:2312. 00206v4 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has recently enabled real-time rendering of unbounded 3D scenes for novel view synthesis.

By Haolin Xiong, Sairisheek Muttukuru, Hanyuan Xiao, Rishi Upadhyay, Pradyumna Chari, Yajie Zhao, Achuta Kadambi

efficiency

arXiv Machine Learning

Jul 2

Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation

arXiv:2607. 01164v1 Announce Type: new Abstract: Recent work has shown that implicit neural representations (INRs) can be trained to effectively compress structured and unstructured volume data, allowing for direct data querying with a reduced memory footprint.

By Landon Dyken, Sharmistha Chakrabarti, Nathan Debardeleben, Steve Petruzza, Qi Wu, Will Usher, Sidharth Kumar

efficiency

arXiv AI

Jul 2

Improving Sparse-View 3DGS Generalization via Flat Minima Optimization

arXiv:2607. 00885v1 Announce Type: cross Abstract: Recent advances in neural rendering have established 3D Gaussian Splatting (3DGS) as a highly efficient representation for novel view synthesis, enabling fast training and real-time rendering with strong fidelity.

By Kangmin Seo, Sangeek Hyun, MinKyu Lee, Jae-Pil Heo

arXiv AI

Jul 10

LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

arXiv:2604. 05182v2 Announce Type: replace-cross Abstract: We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction.

By Zhengqin Li, Cheng Zhang, Jakob Engel, Zhao Dong

llms benchmarks

Hugging Face Trending Papers

Sep 3

Sparse auto-regressive modeling for scene generation from multi-view images

The paper introduces SPAR3S, a sparse voxel‑aligned 3D latent generative model that completes 3D scenes from sparse, unconstrained multi‑view images. By representing only occupied voxels in a compact latent space and training a masked autoregressive transformer with photometric supervision via differentiable 3D Gaussian Splatting, the method predicts missing latent tokens and spatial support, enabling efficient and spatially consistent generation of unseen regions. Experiments on synthetic indoor scenes and RealEstate10k demonstrate higher novel‑view quality and real‑world applicability compared to prior work.

llms diffusion