paper-with-me

Papers

Improving Neural Surface Reconstruction with Feature Priors from Multi-View Image

2024-08-04 · Xinlin Ren, Chenjie Cao, Yanwei Fu, xiangyang xue

Recent advancements in Neural Surface Reconstruction (NSR) have significantly improved multi-view reconstruction when coupled with volume rendering. However, relying solely on photometric consistency in image space falls short of addressing complexities posed by real-world data, including occlusions and non-Lambertian surfaces. To tackle these challenges, we propose an investigation into feature-level consistent loss, aiming to harness valuable feature priors from diverse pretext visual tasks and overcome current limitations. It is crucial to note the existing gap in determining the most effective pretext visual task for enhancing NSR. In this study, we comprehensively explore multi-view feature priors from seven pretext visual tasks, comprising thirteen methods. Our main goal is to strengthen NSR training by considering a wide range of possibilities. Additionally, we examine the impact of varying feature resolutions and evaluate both pixel-wise and patch-wise consistent losses, providing insights into effective strategies for improving NSR performance. By incorporating pre-trained representations from MVSFormer and QuadTree, our approach can generate variations of MVS-NeuS and Match-NeuS, respectively. Our results, analyzed on DTU and EPFL datasets, reveal that feature priors from image matching and multi-view stereo outperform other pretext tasks. Moreover, we discover that extending patch-wise photometric consistency to the feature level surpasses the performance of pixel-wise approaches. These findings underscore the effectiveness of these techniques in enhancing NSR outcomes.

📄 PDF Abstract BibTeX arXiv:2408.02079

Code (1)

maybeLx/MVS_NeuS 공식 구현

Tasks

Surface Reconstruction

Similar Papers 제목 키워드 기반

NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views

2023-12-21 · Han Huang, Yulun Wu, Junsheng Zhou, Ge Gao 외

Recently, neural implicit functions have demonstrated remarkable results in the field of multi-view reconstruction. However, most existing methods are tailored for dense views and exhibit unsatisfactory performance when …

Surface Reconstructionvalid

NeuGrasp: Generalizable Neural Surface Reconstruction with Background Priors for Material-Agnostic Object Grasp Detection

2025-03-05 · Qingyu Fan, Yinghao Cai, Chao Li, Wenzhe He 외

Robotic grasping in scenes with transparent and specular objects presents great challenges for methods relying on accurate depth information. In this paper, we introduce NeuGrasp, a neural surface reconstruction method t…

Robotic GraspingSurface Reconstruction

Spurfies: Sparse Surface Reconstruction using Local Geometry Priors

2024-08-29 · Kevin Raj, Christopher Wewer, Raza Yunus, Eddy Ilg 외

We introduce Spurfies, a novel method for sparse-view surface reconstruction that disentangles appearance and geometry information to utilize local geometry priors trained on synthetic data. Recent research heavily focus…

3D ReconstructionNeRFNovel View SynthesisSurface Reconstruction

Sparis: Neural Implicit Surface Reconstruction of Indoor Scenes from Sparse Views

2025-01-02 · Yulun Wu, Han Huang, Wenyuan Zhang, Chao Deng 외

In recent years, reconstructing indoor scene geometry from multi-view images has achieved encouraging accomplishments. Current methods incorporate monocular priors into neural implicit surface models to achieve high-qual…

Surface Reconstruction

PVP-Recon: Progressive View Planning via Warping Consistency for Sparse-View Surface Reconstruction

2024-09-09 · Sheng Ye, Yuze He, Matthieu Lin, Jenny Sheng 외

Neural implicit representations have revolutionized dense multi-view surface reconstruction, yet their performance significantly diminishes with sparse input views. A few pioneering works have sought to tackle the challe…

Surface Reconstruction