BAGS: Blur agnostic Gaussian splatting through multi-scale kernel modeling

C Peng, Y Tang, Y Zhou, N Wang, X Liu, D Li… - … on Computer Vision, 2025 - Springer
Recent efforts in using 3D Gaussians for scene reconstruction and novel view synthesis can
achieve impressive results on curated benchmarks; however, images captured in real life …

Robust gaussian splatting

F Darmon, L Porzi, S Rota-Bulò… - arXiv preprint arXiv …, 2024 - arxiv.org
In this paper, we address common error sources for 3D Gaussian Splatting (3DGS) including
blur, imperfect camera poses, and color inconsistencies, with the goal of improving its …

Crim-gs: Continuous rigid motion-aware gaussian splatting from motion blur images

J Lee, D Kim, D Lee, S Cho, S Lee - arXiv preprint arXiv:2407.03923, 2024 - arxiv.org
Neural radiance fields (NeRFs) have received significant attention due to their high-quality
novel view rendering ability, prompting research to address various real-world cases. One …

Sparse-DeRF: Deblurred Neural Radiance Fields from Sparse View

D Lee, D Kim, J Lee, M Lee, S Lee, S Lee - arXiv preprint arXiv …, 2024 - arxiv.org
Recent studies construct deblurred neural radiance fields (DeRF) using dozens of blurry
images, which are not practical scenarios if only a limited number of blurry images are …

FusionRF: High-Fidelity Satellite Neural Radiance Fields from Multispectral and Panchromatic Acquisitions

M Sprintson, R Chellappa, C Peng - arXiv preprint arXiv:2409.15132, 2024 - arxiv.org
We introduce FusionRF, a novel neural rendering terrain reconstruction method from
optically unprocessed satellite imagery. While previous methods depend on external …

LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes

Z Qu, K Xu, GP Hancke, RWH Lau - arXiv preprint arXiv:2411.06757, 2024 - arxiv.org
Neural Radiance Fields (NeRFs) have shown remarkable performances in producing novel-
view images from high-quality scene images. However, hand-held low-light photography …

NeRF-FF: a plug-in method to mitigate defocus blur for runtime optimized neural radiance fields

T Wirth, A Rak, M von Buelow, V Knauthe, A Kuijper… - The Visual …, 2024 - Springer
Neural radiance fields (NeRFs) have revolutionized novel view synthesis, leading to an
unprecedented level of realism in rendered images. However, the reconstruction quality of …

An Immersive Multi-Elevation Multi-Seasonal Dataset for 3D Reconstruction and Visualization

X Liu, Y Zhou, Y Guo, R Chellappa, C Peng - arXiv preprint arXiv …, 2024 - arxiv.org
Significant progress has been made in photo-realistic scene reconstruction over recent
years. Various disparate efforts have enabled capabilities such as multi-appearance or large …

CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images

J Lee, S Cho, T Kim, HD Jang, M Lee, G Cha… - arXiv preprint arXiv …, 2024 - arxiv.org
3D Gaussian Splatting (3DGS) has attracted significant attention for its high-quality novel
view rendering, inspiring research to address real-world challenges. While conventional …

fNeRF: High Quality Radiance Fields from Practical Cameras

Y Hua, C Lassner, C Stoll, I Matthews - arXiv preprint arXiv:2406.10633, 2024 - arxiv.org
In recent years, the development of Neural Radiance Fields has enabled a previously
unseen level of photo-realistic 3D reconstruction of scenes and objects from multi-view …