Deep Flow Rendering: View Synthesis via Layer‐aware Reflection Flow

Novel view synthesis (NVS) generates images from unseen viewpoints based on a set of input images. It is a challenge because of inaccurate lighting optimization and geometry inference. Although current neural rendering methods have made significant progress, they still struggle to reconstruct global...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computer graphics forum Ročník 41; číslo 4; s. 139 - 148
Hlavní autori: Dai, Pinxuan, Xie, Ning
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Oxford Blackwell Publishing Ltd 01.07.2022
Predmet:
CCS Concepts
Computing methodologies → Image‐based rendering
Feature extraction
Flow mapping
Illumination
Lighting
Neural networks
Optimization
Reflection
Rendering
Synthesis
Texture mapping
ISSN:0167-7055, 1467-8659
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Novel view synthesis (NVS) generates images from unseen viewpoints based on a set of input images. It is a challenge because of inaccurate lighting optimization and geometry inference. Although current neural rendering methods have made significant progress, they still struggle to reconstruct global illumination effects like reflections and exhibit ambiguous blurs in highly view‐dependent areas. This work addresses high‐quality view synthesis to emphasize reflection on non‐concave surfaces. We propose Deep Flow Rendering that optimizes direct and indirect lighting separately, leveraging texture mapping, appearance flow, and neural rendering. A learnable texture is used to predict view‐independent features, meanwhile enabling efficient reflection extraction. To accurately fit view‐dependent effects, we adopt a constrained neural flow to transfer image‐space features from nearby views to the target view in an edge‐preserving manner. Then we further implement a fusing renderer that utilizes the predictions of both layers to form the output image. The experiments demonstrate that our method outperforms the state‐of‐the‐art methods at synthesizing various scenes with challenging reflection effects.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.14593