SOTAVerified

Intrinsic Image Decomposition

Intrinsic Image Decomposition is the process of separating an image into its formation components such as reflectance (albedo) and shading (illumination). Reflectance is the color of the object, invariant to camera viewpoint and illumination conditions, whereas shading, dependent on camera viewpoint and object geometry, consists of different illumination effects, such as shadows, shading and inter-reflections. Using intrinsic images, instead of the original images, can be beneficial for many computer vision algorithms. For instance, for shape-from-shading algorithms, the shading images contain important visual cues to recover geometry, while for segmentation and detection algorithms, reflectance images can be beneficial as they are independent of confounding illumination effects. Furthermore, intrinsic images are used in a wide range of computational photography applications, such as material recoloring, relighting, retexturing and stylization.

Source: CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 71–80 of 85 papers

TitleStatusHype
Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images—0
Shading Annotations in the Wild—0
DARN: a Deep Adversial Residual Network for Intrinsic Image Decomposition—0
Simultaneous Estimation of Near IR BRDF and Fine-Scale Surface Geometry—0
Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural FieldsCode0
Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression—0
Intrinsic Decomposition of Image Sequences From Local Temporal Variations—0
Intrinsic Scene Decomposition From RGB-D images—0
Learning Ordinal Relationships for Mid-Level Vision—0
Constrained Structured Regression with Convolutional Neural Networks—0
Show:102550
← PrevPage 8 of 9Next →

No leaderboard results yet.