A deep-shallow and global–local multi-feature fusion network for photometric stereo

Liua, Yanru; Ju, Yakun; Jian, Muwei; Gao, Feng; Rao, Yuan; Hu, Yeqi; Dong, Junyu

doi:10.1016/j.imavis.2021.104368

Cited by 25 publications

(12 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al [43] introduced a two-stage deep model, named self-calibrating deep photometric stereo network (SDPS-Net) taking advantage of intermediate supervision. Liu et al [44] enhanced surface normals estimation performance by combining global and local features. Ju et al [45] proposed a normalized attention-weighted photometric stereo network, called NormAttention-PSN, to improve surface orientation prediction performance, especially for complicated surface structures.…”

Section: B Deep Learning-based Photometric Stereomentioning

confidence: 99%

Photometric Stereo Super Resolution via Complex Surface Structure Estimation

Lee,

Kim

2024

IEEE Access

View full text Add to dashboard Cite

Photometric stereo, which derives per-pixel surface normals from shading cues, faces challenges in capturing high-resolution (HR) images in linear response systems. We address the representation of HR surface normals from low-resolution (LR) photometric stereo images. To represent fine details of the surface normal in the HR domain, we propose a novel plug-in high-frequency representation module named the Complex Surface Structure (CSS) estimator. When combined with a conventional photometric stereo model, CSS is capable of representing intricate surface structures in 2D Fourier space. We show that photometric stereo super-resolution (SR) with our CSS estimator provides high-fidelity surface normal representations in higher resolution from the LR inputs. Experiments demonstrate that our results are quantitatively and qualitatively better than those of the existing deep learning-based SR work.

show abstract

Section: B Deep Learning-based Photometric Stereomentioning

confidence: 99%

Photometric Stereo Super Resolution via Complex Surface Structure Estimation

Lee,

Kim

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Traditional photometric stereo methods deal with Lambertian surfaces, with perfectly diffuse reflection. However, photometric stereo methods that deal with non-Lambertian surfaces have also been introduced, either by adopting reflectance models to approximate the non-Lambertian surface properties of objects or based on deep learning [ 39 , 40 , 41 ]. In the case of usage of a single irradiance image, the problem is called shape from shading [ 42 ].…”

Section: Image-based 3d Modelingmentioning

confidence: 99%

An Overview on Image-Based and Scanner-Based 3D Modeling Technologies

Verykokou

Ioannidis

2023

Sensors

View full text Add to dashboard Cite

Advances in the scientific fields of photogrammetry and computer vision have led to the development of automated multi-image methods that solve the problem of 3D reconstruction. Simultaneously, 3D scanners have become a common source of data acquisition for 3D modeling of real objects/scenes/human bodies. This article presents a comprehensive overview of different 3D modeling technologies that may be used to generate 3D reconstructions of outer or inner surfaces of different kinds of targets. In this context, it covers the topics of 3D modeling using images via different methods, it provides a detailed classification of 3D scanners by additionally presenting the basic operating principles of each type of scanner, and it discusses the problem of generating 3D models from scans. Finally, it outlines some applications of 3D modeling, beyond well-established topographic ones.

show abstract

“…We picked computer graph (CG) mesh models Joyful [25] as ground-truth mesh and utilized the same lighting to render 70 images from fixed perspectives using Blender [26]. (5) The EPFL dataset [27] provides two ground-truth meshes captured by LIDAR sensors, namely, Herz-Jesu-P8 and Fountain-P11, and provides the images registered with the meshes. (6) Personal Collection Dataset.…”

Section: Dataset and Evaluation Metricsmentioning

confidence: 99%

“…Photometric stereo [1,2] and mesh refinement are popular methods to reconstruct high-quality mesh shapes. Photometric stereo recovers pixel-wise surface normals from a fixed scene under varying shading cues, which are widely used in the industrial field [3][4][5]. The mesh refinement method evolves the initial mesh to fine details using multiview images.…”

Section: Introductionmentioning

confidence: 99%

Total Differential Photometric Mesh Refinement with Self-Adapted Mesh Denoising

Yan

Yang

et al. 2022

Photonics

View full text Add to dashboard Cite

Variational mesh refinement is a crucial step in multiview 3D reconstruction. Existing algorithms either focus on recovering mesh details or focus on suppressing noise. Approaches with consideration of both are lacking. To address this limitation, we proposed a new variational mesh refinement method named total differential mesh refinement (TDR), which mainly included two improvements. First, the traditional partial-differential photo-consistency gradient used in the variational mesh refinement method was replaced by the proposed total-differential photo-consistency gradient. With consideration of the photo-consistency correlation between adjacent pixels, our method can make photo-consistency achieve a more effective convergence than traditional approaches. Second, we introduced the bilateral normal filter with a novel self-adaptive mesh denoising strategy into the variational mesh refinement. This strategy maintains a balance between detail preservation and effective denoising via the zero-normalized cross-correlation (ZNCC) map. Various experiments demonstrated that our method is superior to traditional variational mesh refinement approaches in both accuracy and denoising effect. Moreover, compared with the mesh generated by open-source and commercial software (Context Capture), our meshes are more detailed, regular, and smooth.

show abstract

A deep-shallow and global–local multi-feature fusion network for photometric stereo

Cited by 25 publications

References 28 publications

Photometric Stereo Super Resolution via Complex Surface Structure Estimation

Photometric Stereo Super Resolution via Complex Surface Structure Estimation

An Overview on Image-Based and Scanner-Based 3D Modeling Technologies

Total Differential Photometric Mesh Refinement with Self-Adapted Mesh Denoising

Contact Info

Product

Resources

About