10 papers · 1 filter
NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-Light Novel View Synthesis
Shaurya Pavan A, Vemunuri Divya Madhuri, Yash Pradeep Gawande +1
Reconstructing 3D scenes under real-world low-light conditions remains challenging due to severe sensor noise, low signal-to-noise ratios, and degraded photometric consistency, whi…
PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blur
Gopi Raju Matta, Reddypalli Trisha, Vemunuri Divya Madhuri +1
We address the inverse problem of blind 3D scene reconstruction from extremely motion-blurred images, a scenario where traditional Structure-from-Motion (SfM) pipelines fail. Exist…
GeMS: Efficient Gaussian Splatting for Extreme Motion Blur
Gopi Raju Matta, Trisha Reddypalli, Vemunuri Divya Madhuri +1
We introduce GeMS, a framework for 3D Gaussian Splatting (3DGS) designed to handle severely motion-blurred images. State-of-the-art deblurring methods for extreme blur, such as ExB…
RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement
Raman Jha, Adithya Lenka, Mani Ramanagopal +2
In nighttime conditions, high noise levels and bright illumination sources degrade image quality, making low-light image enhancement challenging. Thermal images provide complementa…
BeSplat: Gaussian Splatting from a Single Blurry Image and Event Stream
Gopi Raju Matta, Reddypalli Trisha, Kaushik Mitra
Novel view synthesis has been greatly enhanced by the development of radiance field methods. The introduction of 3D Gaussian Splatting (3DGS) has effectively addressed key challeng…
GN-FR:Generalizable Neural Radiance Fields for Flare Removal
Gopi Raju Matta, Rahul Siddartha, Rongali Simhachala Venkata Girish +2
Flare, an optical phenomenon resulting from unwanted scattering and reflections within a lens system, presents a significant challenge in imaging. The diverse patterns of flares, s…