Shape from Shading: A Survey

By Ruo Zhang, Ping-Sing Tsai, J. Cryer, Mubarak Shah. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning to Reconstruct Shapes from Unseen Classes (2018, background): “Through years, researchers have explored recovering 2.5D sketches from texture, shading, or color images [Barron and Malik, 2015, Bell et al., 2014, Horn and Brooks, 1989, Tappen et al., 2003, Weiss, 2001, Zhang et al., 1999].”
Learning Shape Priors for Single-View 3D Completion and Reconstruction (2018, background): “In the past, researchers have explored recovering 2.5D sketches from shading, texture, or color images [2,3,20,47,55,63].”
MarrNet: 3D Shape Reconstruction via 2.5D Sketches (2017, background): “In the past, researchers have explored recovering 2.5D shape from shading, texture, or color images [Horn and Brooks, 1989, Zhang et al., 1999, Tappen et al., 2003, Barron and Malik, 2015, Weiss, 2001, Bell et al., 2014].”
Deeper Depth Prediction with Fully Convolutional Residual Networks (2016, background): “ing image pairs of the same scene to reconstruct 3D shapes. In the single-view case, most approaches relied on motion (Structure-from-Motion [34]) or different shooting conditions (Shape-from-Shading [39], Shape-from-Defocus [33]). Despite the ambiguities that arise in lack of such information, but ”
Modeling the space of camera response functions (2004, background): “…construction of linear high-dynamic range images [3], [21], [26], [6], [22], photometric stereo [2], [28], [31], shape from shading [17], [28], [33], estimation of reflectance and illumination from shape and intensity [20], recovery of BRDF from images [4], [7], [25], [29], [32], and surface…”
3-D Depth Reconstruction from a Single Still Image (2007, background): “Methods such as shape from shading [12; 13] and shape from texture [14; 15; 16] generally assume uniform color and/or texture, 1 and hence would perform very poorly on the complex, unconstrained, highly textured images that we consider.”
A Surface Deformation Framework for 3D Shape Recovery (2006, methodology): “On the other hand, shape from shading methods are based on the diffusing properties of Lambertian surfaces [17].”
DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition (2017, background): “Understanding the three dimensional shape or spatial layout of a real-world object captured in a 2D image has been a classic computer vision problem for decades [5, 12, 45].”
Noise Estimation from a Single Image (2006, background): “Examples of algorithms requiring noise level estimates include motion estimation [1], denoising [12, 11], super-resolution [5], shape-from-shading [19], and feature extraction [9].”
Real-time shading-based refinement for consumer depth cameras (2014, methodology): “Most of these methods rely on heuristic assumptions about the correlation of color and depth, e.g., that edges in both channels likely coincide.”
Deep Depth Completion of a Single RGB-D Image (2018, methodology): “Classic methods include shape-from-shading [78] and shape-from-defocus [67].”
MonoScene: Monocular 3D Semantic Scene Completion (2021, background): “Despite early researches [31,57, 80], in the deep learning era the first works focused on single 3D object reconstruction with explicit [1, 11, 16, 23, 26,”
Optical techniques for 3D surface reconstruction in computer-assisted laparoscopic surgery (2013, background): “The vast majority of SfS methods only use a single input image (Zhang et al., 1999).”
Tex2Shape: Detailed Full Human Body Geometry From a Single Image (2019, methodology): “Shape-from-shading [60] allows to invert the process and estimate the surface from shading, which was used before to refine geometry of stereobased [55] or multi-view-based human performance capture results [56, 29].”