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

• URL: http://arxiv.org/abs/2602.24065v2
• Date: Wed, 04 Mar 2026 08:09:21 GMT
• Title: EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setups
• Authors: Zaiyan Yang, Jieji Ren, Xiangyi Wang, zonglin li, Xu Cao, Heng Guo, Zhanyu Ma, Boxin Shi,
• Abstract summary: Multiview photometric stereo (MVPS) and multiview shape from polarization (MVSfP) have not been quantitatively assessed together with MVS.<n>We propose EvalMVX, a real-world dataset containing $25$ objects, each captured with a polarized camera under $20$ varying views.<n>We evaluate $13$ MVX methods published in recent years, record the best-performing methods, and identify open problems under diverse geometric details.
• Score: 76.30400481133215
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Multi-view Surface Reconstruction Using Normal and Reflectance Cues [3.3190807913214293]
  We introduce a versatile framework that incorporates multi-view normal and optionally reflectance maps into radiance-based surface reconstruction.<n>Our approach employs a pixel-wise joint re-parametrization of reflectance and surface normals, representing them as a vector of radiances under simulated, varying illumination.<n>Our method excels in reconstructing fine-grained details and handling challenging visibility conditions.
  arXiv  Detail & Related papers  (2025-06-04T16:09:16Z)
• MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model [87.71060849866093]
  We introduce MVGenMaster, a multi-view diffusion model enhanced with 3D priors to address versatile Novel View Synthesis (NVS) tasks.<n>Our model features a simple yet effective pipeline that can generate up to 100 novel views conditioned on variable reference views and camera poses.<n>We present several training and model modifications to strengthen the model with scaled-up datasets.
  arXiv  Detail & Related papers  (2024-11-25T07:34:23Z)
• DUSt3R: Geometric 3D Vision Made Easy [8.471330244002564]
  We introduce DUSt3R, a novel paradigm for Dense and Unconstrained Stereo 3D Reconstruction of arbitrary image collections.<n>We show that this formulation smoothly unifies the monocular and binocular reconstruction cases.<n>Our formulation directly provides a 3D model of the scene as well as depth information, but interestingly, we can seamlessly recover from it, pixel matches, relative and absolute camera.
  arXiv  Detail & Related papers  (2023-12-21T18:52:14Z)
• Multiview Stereo with Cascaded Epipolar RAFT [73.7619703879639]
  We address multiview stereo (MVS), an important 3D vision task that reconstructs a 3D model such as a dense point cloud from multiple calibrated images. We propose CER-MVS, a new approach based on the RAFT (Recurrent All-Pairs Field Transforms) architecture developed for optical flow. CER-MVS introduces five new changes to RAFT: epipolar cost volumes, cost volume cascading, multiview fusion of cost volumes, dynamic supervision, and multiresolution fusion of depth maps.
  arXiv  Detail & Related papers  (2022-05-09T18:17:05Z)
• RayMVSNet: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo [35.22032072756035]
  RayMVSNet learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth. Our method ranks top on both the DTU and the Tanks & Temples datasets over all previous learning-based methods.
  arXiv  Detail & Related papers  (2022-04-04T08:43:38Z)
• VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion [68.68537312256144]
  VoRTX is an end-to-end volumetric 3D reconstruction network using transformers for wide-baseline, multi-view feature fusion. We train our model on ScanNet and show that it produces better reconstructions than state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-12-01T02:18:11Z)
• Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo [103.08512487830669]
  We present a modern solution to the multi-view photometric stereo problem (MVPS) We procure the surface orientation using a photometric stereo (PS) image formation model and blend it with a multi-view neural radiance field representation to recover the object's surface geometry. Our method performs neural rendering of multi-view images while utilizing surface normals estimated by a deep photometric stereo network.
  arXiv  Detail & Related papers  (2021-10-11T20:20:03Z)
• Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials [65.95928593628128]
  We present a method to capture both 3D shape and spatially varying reflectance with a multi-view photometric stereo technique. Our algorithm is suitable for perspective cameras and nearby point light sources.
  arXiv  Detail & Related papers  (2020-01-18T12:26:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.