1 code implementation • CVPR 2023 • Seunghyeon Seo, Donghoon Han, Yeonjin Chang, Nojun Kwak
In this work, we propose MixNeRF, an effective training strategy for novel view synthesis from sparse inputs by modeling a ray with a mixture density model.
1 code implementation • ICCV 2023 • Seunghyeon Seo, Yeonjin Chang, Nojun Kwak
Neural Radiance Field (NeRF) has been a mainstream in novel view synthesis with its remarkable quality of rendered images and simple architecture.
no code implementations • 29 Sep 2022 • Jookyung Song, Yeonjin Chang, SeongUk Park, Nojun Kwak
U-net, a conventional approach for conditional GANs, retains fine details of unmasked regions but the style of the reconstructed image is inconsistent with the rest of the original image and only works robustly when the size of the occluding object is small enough.
no code implementations • 7 Nov 2023 • Yeonjin Chang, Yearim Kim, Seunghyeon Seo, Jung Yi, Nojun Kwak
In this work, we introduce our method of outdoor scene relighting for Neural Radiance Fields (NeRF) named Sun-aligned Relighting TensoRF (SR-TensoRF).
no code implementations • 16 Mar 2024 • Seunghyeon Seo, Yeonjin Chang, Jayeon Yoo, Seungwoo Lee, Hojun Lee, Nojun Kwak
Addressing this, we propose HourglassNeRF, an effective regularization-based approach with a novel hourglass casting strategy.