https://github.com/FuxiComputerVision/Nefii
공식 코드NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Image relighting involves changing the illumination settings of an image.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination
Extracting Triangular 3D Models, Materials, and Lighting From Images
Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising
Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark
Deep Relighting Networks for Image Light Source Manipulation
Nighttime Person Re-Identification via Collaborative Enhancement Network with Multi-domain Learning
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
NeRD: Neural Reflectance Decomposition from Image Collections
S3Net: A Single Stream Structure for Depth Guided Image Relighting
LBM: Latent Bridge Matching for Fast Image-to-Image Translation
NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination
DNF-Avatar: Distilling Neural Fields for Real-time Animatable Avatar Relighting
DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images
AIM 2020: Scene Relighting and Illumination Estimation Challenge
Scene relighting with illumination estimation in the latent space on an encoder-decoder scheme
Multi-scale Self-calibrated Network for Image Light Source Transfer
Designing An Illumination-Aware Network for Deep Image Relighting
GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing
Multi-modal Bifurcated Network for Depth Guided Image Relighting
A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
Relighting Images in the Wild with a Self-Supervised Siamese Auto-Encoder
Bi-Mix: Bidirectional Mixing for Domain Adaptive Nighttime Semantic Segmentation
Multi-modal Bifurcated Network for Depth Guided Image Relighting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.