2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2022 · 117 citations · 49 references
ComputingComputer ScienceComputer VisionMachine VisionVisual Perception3D RenderingImage SynthesisOcclusion HandlingNeural Radiance FieldsNeural View SynthesisNovel View GenerationNovel View RenderingRadianceView SynthesisViews
Neural Radiance Fields (NeRF) has recently gained popularity for its impressive novel view synthesis ability. This paper studies the problem of hallucinated NeRF: i.e., recovering a realistic NeRF at a different time of day from a group of tourism images. Existing solutions adopt NeRF with a controllable appearance embedding to render novel views under various conditions, but they cannot render view-consistent images with an unseen appearance. To solve this problem, we present an end-to-end framework for constructing a hallucinated NeRF, dubbed as Ha-NeRF. Specifically, we propose an appearance hallucination module to handle time-varying appearances and transfer them to novel views. Considering the complex occlusions of tourism images, we introduce an anti-occlusion module to decompose the static subjects for visibility accurately. Experimental results on synthetic data and real tourism photo collections demonstrate that our method can hallucinate the desired appearances and render occlusion-free images from different views. The project and supplementary materials are available at https://rover-xingyu.github.io/Ha-NeRF/.
49
Marc Levoy, Pat Hanrahan · 1996 · 3.7K citations · Full text
pixelNeRF: Neural Radiance Fields from One or Few Images
Alex Yu, Vickie Ye, Matthew Tancik et al. · 2021 · 1.4K citations
Leonard McMillan, Gary Bishop · 1995 · 1.3K citations
Unstructured lumigraph rendering
Chris Buehler, Michael Bosse, Leonard McMillan et al. · 2001 · 889 citations · Full text