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 1–50 of 85 papers

TitleStatusHype
Colorful Diffuse Intrinsic Image Decomposition in the WildCode3
Intrinsic Image Decomposition via Ordinal ShadingCode2
DPF: Learning Dense Prediction Fields with Weak SupervisionCode1
A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse RenderingCode1
EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised TrainingCode1
Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware LearningCode1
Exploiting Diffusion Prior for Generalizable Dense PredictionCode1
Complementary Feature Enhanced Network with Vision Transformer for Image DehazingCode1
Illumination-Aware Image Quality Assessment for Enhanced Low-light ImageCode1
Intrinsic Image Decomposition Using Point Cloud RepresentationCode1
Intrinsic Decomposition of Document Images In-the-WildCode1
Outdoor inverse rendering from a single image using multiview self-supervisionCode1
Physically Inspired Dense Fusion Networks for RelightingCode1
PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image DecompositionCode1
PS-Diffusion: Photorealistic Subject-Driven Image Editing with Disentangled Control and AttentionCode1
Seeing a Rose in Five Thousand WaysCode1
Creating a Forensic Database of Shoeprints from Online Shoe Tread PhotosCode1
Unsupervised Learning for Intrinsic Image Decomposition from a Single ImageCode1
DeRenderNet: Intrinsic Image Decomposition of Urban Scenes with Shape-(In)dependent Shading Rendering—0
Discriminative feature encoding for intrinsic image decomposition—0
Separate In Latent Space: Unsupervised Single Image Layer Separation—0
CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering—0
CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition—0
A deep learning based interactive sketching system for fashion images design—0
Color naming guided intrinsic image decomposition—0
Complementary Intrinsics From Neural Radiance Fields and CNNs for Outdoor Scene Relighting—0
Consistency-aware Shading Orders Selective Fusion for Intrinsic Image Decomposition—0
Constrained Structured Regression with Convolutional Neural Networks—0
DARN: a Deep Adversial Residual Network for Intrinsic Image Decomposition—0
Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition—0
Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression—0
Shadow Removal from Single RGB-D Images—0
Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training—0
Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow—0
Free Supervision From Video Games—0
GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition—0
Simultaneous Estimation of Near IR BRDF and Fine-Scale Surface Geometry—0
IntrinSeqNet: Learning to Estimate the Reflectance from Varying Illumination—0
Single Image Intrinsic Decomposition without a Single Intrinsic Image—0
Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition—0
Single Image Layer Separation using Relative Smoothness—0
Intrinsic Decomposition of Image Sequences From Local Temporal Variations—0
Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces—0
Intrinsic Image Decomposition using Paradigms—0
3D Face Mask Presentation Attack Detection Based on Intrinsic Image Analysis—0
Intrinsic Image Transformation via Scale Space Decomposition—0
Intrinsic Scene Decomposition From RGB-D images—0
Invariant Descriptors for Intrinsic Reflectance Optimization—0
JoIN: Joint GANs Inversion for Intrinsic Image Decomposition—0
Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.