13 papers
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…
PhotonSplat: 3D Scene Reconstruction and Colorization from SPAD Sensors
Sai Sri Teja, Sreevidya Chintalapati, Vinayak Gupta +4
Advances in 3D reconstruction using neural rendering have enabled high-quality 3D capture. However, they often fail when the input imagery is corrupted by motion blur, due to fast…
SPC to 3D: Novel View Synthesis from Binary SPC via I2I translation
Sumit Sharma, Gopi Raju Matta, Kaushik Mitra
Single Photon Avalanche Diodes (SPADs) represent a cutting-edge imaging technology, capable of detecting individual photons with remarkable timing precision. Building on this sensi…
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…
Transforming Single Photon Camera Images to Color High Dynamic Range Images
Sumit Sharma, Girish Rongali, Kaushik Mitra
Traditional CMOS sensors suffer from restricted dynamic range and sub optimal performance under extreme lighting conditions. They are affected by electronic noise in low light cond…
U2NeRF: Unsupervised Underwater Image Restoration and Neural Radiance Fields
Vinayak Gupta, Manoj S, Mukund Varma T +1
Underwater images suffer from colour shifts, low contrast, and haziness due to light absorption, refraction, scattering and restoring these images has warranted much attention. In…
GANESH: Generalizable NeRF for Lensless Imaging
Rakesh Raj Madavan, Akshat Kaimal, Badhrinarayanan K +4
Lensless imaging offers a significant opportunity to develop ultra-compact cameras by removing the conventional bulky lens system. However, without a focusing element, the sensor's…
GAURA: Generalizable Approach for Unified Restoration and Rendering of Arbitrary Views
Vinayak Gupta, Rongali Simhachala Venkata Girish, Mukund Varma T +2
Neural rendering methods can achieve near-photorealistic image synthesis of scenes from posed input images. However, when the images are imperfect, e.g., captured in very low-light…
MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results
Yuekun Dai, Dafeng Zhang, Xiaoming Li +60
The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algor…