EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setups

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Zaiyan, Ren, Jieji, Wang, Xiangyi, li, zonglin, Cao, Xu, Guo, Heng, Ma, Zhanyu, Shi, Boxin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911483417329664
author Yang, Zaiyan
Ren, Jieji
Wang, Xiangyi
li, zonglin
Cao, Xu
Guo, Heng
Ma, Zhanyu
Shi, Boxin
author_facet Yang, Zaiyan
Ren, Jieji
Wang, Xiangyi
li, zonglin
Cao, Xu
Guo, Heng
Ma, Zhanyu
Shi, Boxin
contents Recent advancements in neural surface reconstruction have significantly enhanced 3D reconstruction. However, current real world datasets mainly focus on benchmarking multiview stereo (MVS) based on RGB inputs. Multiview photometric stereo (MVPS) and multiview shape from polarization (MVSfP), though indispensable on high-fidelity surface reconstruction and sparse inputs, have not been quantitatively assessed together with MVS. To determine the working range of different MVX (MVS, MVSfP, and MVPS) techniques, we propose EvalMVX, a real-world dataset containing $25$ objects, each captured with a polarized camera under $20$ varying views and $17$ light conditions including OLAT and natural illumination, leading to $8,500$ images. Each object includes aligned ground-truth 3D mesh, facilitating quantitative benchmarking of MVX methods simultaneously. Based on our EvalMVX, we evaluate $13$ MVX methods published in recent years, record the best-performing methods, and identify open problems under diverse geometric details and reflectance types. We hope EvalMVX and the benchmarking results can inspire future research on multiview 3D reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2602_24065
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setups
Yang, Zaiyan
Ren, Jieji
Wang, Xiangyi
li, zonglin
Cao, Xu
Guo, Heng
Ma, Zhanyu
Shi, Boxin
Computer Vision and Pattern Recognition
Recent advancements in neural surface reconstruction have significantly enhanced 3D reconstruction. However, current real world datasets mainly focus on benchmarking multiview stereo (MVS) based on RGB inputs. Multiview photometric stereo (MVPS) and multiview shape from polarization (MVSfP), though indispensable on high-fidelity surface reconstruction and sparse inputs, have not been quantitatively assessed together with MVS. To determine the working range of different MVX (MVS, MVSfP, and MVPS) techniques, we propose EvalMVX, a real-world dataset containing $25$ objects, each captured with a polarized camera under $20$ varying views and $17$ light conditions including OLAT and natural illumination, leading to $8,500$ images. Each object includes aligned ground-truth 3D mesh, facilitating quantitative benchmarking of MVX methods simultaneously. Based on our EvalMVX, we evaluate $13$ MVX methods published in recent years, record the best-performing methods, and identify open problems under diverse geometric details and reflectance types. We hope EvalMVX and the benchmarking results can inspire future research on multiview 3D reconstruction.
title EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setups
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.24065