Lee, SeokYeong Choi, JunYong Kim, Seungryong Kim, Ig-Jae Cho, Junghyun 2024-09-19T02:30:14Z 2024-09-19T02:30:14Z 2024-09-19 2024-02 2159-5399 https://pubs.kist.re.kr/handle/201004/150632 https://underline.io/events/439/sessions/17372/lecture/91744-few-shot-neural-radiance-fields-under-unconstrained-illumination In this paper, we introduce a new challenge for synthesizing novel view images in practical environments with limited input multi-view images and varying lighting conditions. Neural radiance fields (NeRF), one of the pioneering works for this task, demand an extensive set of multi-view images taken under constrained illumination, which is often unattainable in real-world settings. While some previous works have managed to synthesize novel views given images with different illumination, their performance still relies on a substantial number of input multi-view images. To address this problem, we suggest ExtremeNeRF, which utilizes multi-view albedo consistency, supported by geometric alignment. Specifically, we extract intrinsic image components that should be illumination-invariant across different views, enabling direct appearance comparison between the input and novel view under unconstrained illumination. We offer thorough experimental results for task evaluation, employing the newly created NeRF Extreme benchmark-the first in-the-wild benchmark for novel view synthesis under multiple viewing directions and varying illuminations. English ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE Few-Shot Neural Radiance Fields under Unconstrained Illumination Conference 1 38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence, pp.2938 - 2946 38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence 2938 2946 US Vancouver, CANADA 2024-02-20 THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 4 001239884400007