Ieee Transactions on Pattern Analysis and Machine Intelligence Shape, Illumination, and Reflectance from Shading

Subfields: Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding (2020, methodology): “These distributions roughly agree with common priors on reflectance and illumination found in the inverse rendering literature [11, 13].”
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture (2014, methodology): “[21], Barron and Malik [3, 2], and most recently by Wang et al.”
Learning Shape Priors for Single-View 3D Completion and Reconstruction (2018, background): “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].”
3D Shape Induction from 2D Views of Multiple Objects (2016, background): “Optimization-based approaches put priors on geometry, material, and light and estimate all of them by minimizing the reconstruction error when rendered [17, 3, 2].”
Category-specific object reconstruction from a single image (2014, methodology): “We propose an additional processing step to recover high frequency shape information by adapting the intrinsic images algorithm of Barron and Malik [6, 5], SIRFS, which exploits statistical regularities between shapes, reflectance and illumination Formally, SIRFS is formulated as the following optim”
Taskonomy: Disentangling Task Transfer Learning (2018, methodology): “Reshading One way to infer scene geometry is “shape from shading” [3] using the intrinsic image decomposition I = A · S, where S is a shading function parameterized by lighting and depth.”
Multi-view 3D Models from Single Images with a Convolutional Network (2015, background): “A general approach is to use certain models of lighting, reflectance and object properties to disentangle these factors given a 2D input image [15].”
Picture: A probabilistic programming language for scene perception (2015, methodology): “We asked CAD experts to manually generate CAD model fits to these im ages in Blender, and evaluated our approach in compari son to a state-of-the-art 3D surface reconstruction algorithm from [3](SIRFS).”
Crisp Boundary Detection Using Pointwise Mutual Information (2014, methodology): “Object boundary cues have been used to aid in segmentation [1,2,3], object detection and recognition [4,5], and recovery of intrinsic scene properties such as shape, reflectance, and illumination [6].”
Learning to Recover 3D Scene Shape from a Single Image (2020, background): “A number of works have addressed reconstructing different types of objects from a single image [2, 39, 42], such as humans [30, 31], cars, planes, tables, etc.”
Learning to Navigate the Energy Landscape (2016, methodology): “Recent years have seen the re-emergence of the ‘analysis by synthesis’ or ’inverse graphics’ approach to Computer Vision problems [3, 41, 38, 26, 20, 42, 43].”
Deep Single-Image Portrait Relighting (2019, methodology): “, longer exposure time may lead to a SH with high energy under the same lighting conditions), we proposed to use a scale invariant Mean Squared Error (Si-MSE) [4] to evaluate the error between the generated image I∗t and the ground truth image It.”