Intrinsic Image Decomposition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Intrinsic Image Decomposition using Paradigms
A deep learning based interactive sketching system for fashion images design
Physics-based Shading Reconstruction for Intrinsic Image Decomposition
Towards Geometry Guided Neural Relighting with Flash Photography
Learning to Factorize and Relight a City
Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition
ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition
Unsupervised Learning for Intrinsic Image Decomposition from a Single Image
Leveraging Multi-view Image Sets for Unsupervised Intrinsic Image Decomposition and Highlight Separation
IntrinSeqNet: Learning to Estimate the Reflectance from Varying Illumination
Separate In Latent Space: Unsupervised Single Image Layer Separation
3D Face Mask Presentation Attack Detection Based on Intrinsic Image Analysis
Semantic Hierarchical Priors for Intrinsic Image Decomposition
Consistency-aware Shading Orders Selective Fusion for Intrinsic Image Decomposition
Color naming guided intrinsic image decomposition
CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering
Learning Blind Video Temporal Consistency
Joint Learning of Intrinsic Images and Semantic Segmentation
Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition
Intrinsic Image Transformation via Scale Space Decomposition
Learning Intrinsic Image Decomposition from Watching the World
CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition
Self-Supervised Intrinsic Image Decomposition
Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images
Shading Annotations in the Wild
DARN: a Deep Adversial Residual Network for Intrinsic Image Decomposition
Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields
Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression
Constrained Structured Regression with Convolutional Neural Networks
Learning Data-driven Reflectance Priors for Intrinsic Image Decomposition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.