SHAPE FROM SHADING: A METHOD FOR OBTAINING THE SHAPE OF A SMOOTH OPAQUE OBJECT FROM ONE VIEW

By Berthold K. P. Horn. 1970

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

Lifting Object Detection Datasets into 3D (2015, background): “Methods such as shape from shading (SfS) [43] hold great promise but have so far been applied only in very restricted settings as they make strong assumptions about global illumination conditions and the reﬂective properties of the object.”
Intrinsic Scene Properties from a Single RGB-D Image (2013, background): “SIRFS can be thought of as an extension of classic shape-from-shading models [14] in which reflectance and illumination are recovered in addition to shape.”
Shape from Shading: A Survey (1999, methodology): “Horn's characteristic strip method [17] is essentially a propagation method.”
Color Constancy, Intrinsic Images, and Shape Estimation (2012, background): “Another special case of intrinsic images is shape-from-shading (SFS) [16], in which reflectance and illumination are assumed to be known and shape is recovered.”
Ieee Transactions on Pattern Analysis and Machine Intelligence Shape, Illumination, and Reflectance from Shading (unknown): “SIRFS can be thought of as an extension of classic shape-from-shading models [44] in which not only shape, but reflectance and illumination are unknown.”
Optical techniques for 3D surface reconstruction in computer-assisted laparoscopic surgery (2013, background): “SfS has been studied since the early seventies (Horn, 1970).”
Shape, albedo, and illumination from a single image of an unknown object (2012, methodology): “Our model relates to the classic shape-from-shading problem [15] as we rely on shading as a cue for depth, but SFS techniques generally require albedo and illumination to be known, which we do not.”
Single image portrait relighting (2019, background): “Shape-from-shading solutions assume that materials and illumination are known or fixed and attempt to recover only geometry [Horn 1970].”
NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis (2020, background): “The resulting Neural Reﬂectance and Visibility Field (NeRV) is visualized in Figure 3.”
What Do Single-View 3D Reconstruction Networks Learn? (2019, background): “Historically, single-image 3D reconstruction has been approached via shape-from-shading [6, 16, 57].”
Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches (2021, background): “Early approaches utilize perceptual cues, such as shading [14] and texture [39], to get a clue about surface orientations.”
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization (2020, methodology): “Then, ﬁne details represented as surface normal [51] or displacements [3] are added by either a post-process such as Shape From Shading [14] or composition within neural networks.”
Object Recognition in the Geometric Era: A Retrospective (2006, background): “There was not much interest in explaining image intensity variations except for the early work by Horn [33].”
Efficiently combining positions and normals for precise 3D geometry (2005, methodology): “Orientation measurement: The photometric stereo method [Woodham 1980], which obtains surface orientation from shading information, is part of a larger set of methods known as shape-fromshading [Horn 1970].”
How Little Do We Need for 3-D Shape Perception? (2011, methodology): “Lastly, the computational approach to the shape-from-shading problem was pioneered by Horn and colleagues (Horn 1970; Ikeuchi and Horn 1981; Horn and Brooks 1989).”
Learning Category-Specific Deformable 3D Models for Object Reconstruction (2017, background): “Index Terms—Object reconstruction, 3D shape modeling, viewpoint estimation, scene understanding Ç”