Conceitos Básicos
Recovering geometry, material properties, and illumination from multi-view images using NeuS-PIR method.
Resumo
This paper introduces NeuS-PIR for reconstructing relightable neural surfaces. It utilizes implicit neural surface representation to factorize geometry, material, and illumination. The method distills indirect illumination fields and enables advanced applications like relighting. Experimental results show superiority over existing methods.
-
Introduction
- Inverse rendering challenges in computer vision.
- Importance of recovered properties for various applications.
-
Methodology
- Utilizing NeuS for geometry reconstruction.
- Joint optimization with pre-integrated rendering for material and illumination.
-
Data Extraction
- "Our method excels in relighting the image and reconstructing geometry."
-
Related Work
- Comparison with explicit reconstruction methods.
- Advancements in neural surface reconstruction.
-
Experiments
- Evaluation on synthetic datasets (NeRFactor) and real-world CO3D dataset.
-
Ablation Study
- Impact of material and SDF regularization on performance.
-
Indirect Illumination
- Distillation of indirect illumination fields for complex lighting effects.
Estatísticas
"Our method excels in relighting the image and reconstructing geometry."
Citações
"Our method excels in relighting the image and reconstructing geometry."