Lune

CVPR Findings2026

NeVStereo: A NeRF-Driven NVS-Stereo Architecture for High-Fidelity 3D Tasks

Pengcheng Chen, Yue Hu, Wenhao Li, Nicole M Gunderson, Andrew Feng, Zhenglong Sun, Peter Beerel, Eric J Seibel

Abstract

thesis, and surface reconstruction from multi-view RGBonly inputs. NeVStereo combines NeRF-based NVS for stereo-friendly renderings, confidence-guided multi-view depth estimation, NeRF-coupled bundle adjustment for pose refinement, and an iterative refinement stage that updates both depth and the radiance field to improve geometric consistency. This design mitigated the common NeRF-based issues such as surface stacking, artifacts, and pose-depth coupling. Across indoor, outdoor, tabletop, and aerial benchmarks, our experiments indicate that NeVStereo achieves consistently strong zero-shot performance, with up to 36% lower depth error, 10.4% improved pose accuracy, 4.5% higher NVS fidelity, and state-of-theart mesh quality (F1 91.93%, Chamfer 4.35 mm) compared to existing prestigious methods.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • NICE-SLAM: Neural Implicit Scalable Encoding for SLAM cites DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras
  • NICE-SLAM: Neural Implicit Scalable Encoding for SLAM cites NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on24

  1. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  2. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt et al.NeurIPS 2021 · 2,500 citations
  3. DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D CamerasZachary Teed, Jia DengNeurIPS 2021 · 1,248 citations
  4. Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.ICCV 2023 · 799 citations
  5. NICE-SLAM: Neural Implicit Scalable Encoding for SLAMZihan Zhu, Songyou Peng, Viktor Larsson, Weiwei Xu et al.CVPR 2022 · 720 citations

Related papers

  1. NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view StereoYi Wei, Shaohui Liu, Yongming Rao, Wang Zhao et al.ICCV 2021 · 286 citations
  2. Generalizable Novel-View Synthesis Using a Stereo CameraHaechan Lee, Wonjoon Jin, Seung-Hwan Baek, Sunghyun ChoCVPR 2024
  3. SPARF: Neural Radiance Fields from Sparse and Noisy PosesPrune Truong, Marie-Julie Rakotosaona, Fabian Manhardt, Federico TombariCVPR 2023
  4. DäRF: Boosting Radiance Fields from Sparse Input Views with Monocular Depth AdaptationJiuhn Song, Seonghoon Park, Honggyu An, Seokju Cho et al.NeurIPS 2023 · 11 citations
  5. Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse ViewsJiang Wu, Rui Li, Yu Zhu, Rong Guo et al.CVPR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines