paper-with-me

Papers

HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting

2024-05-24 · Yuanhao Cai, Zihao Xiao, Yixun Liang, Minghan Qin, Yulun Zhang, Xiaokang Yang, Yaoyao Liu, Alan Yuille

High dynamic range (HDR) novel view synthesis (NVS) aims to create photorealistic images from novel viewpoints using HDR imaging techniques. The rendered HDR images capture a wider range of brightness levels containing more details of the scene than normal low dynamic range (LDR) images. Existing HDR NVS methods are mainly based on NeRF. They suffer from long training time and slow inference speed. In this paper, we propose a new framework, High Dynamic Range Gaussian Splatting (HDR-GS), which can efficiently render novel HDR views and reconstruct LDR images with a user input exposure time. Specifically, we design a Dual Dynamic Range (DDR) Gaussian point cloud model that uses spherical harmonics to fit HDR color and employs an MLP-based tone-mapper to render LDR color. The HDR and LDR colors are then fed into two Parallel Differentiable Rasterization (PDR) processes to reconstruct HDR and LDR views. To establish the data foundation for the research of 3D Gaussian splatting-based methods in HDR NVS, we recalibrate the camera parameters and compute the initial positions for Gaussian point clouds. Experiments demonstrate that our HDR-GS surpasses the state-of-the-art NeRF-based method by 3.84 and 1.91 dB on LDR and HDR NVS while enjoying 1000x inference speed and only requiring 6.3% training time. Code and recalibrated data will be publicly available at https://github.com/caiyuanhao1998/HDR-GS . A brief video introduction of our work is available at https://youtu.be/wtU7Kcwe7ck

📄 PDF Abstract BibTeX arXiv:2405.15125

Code (2)

caiyuanhao1998/hdr-gs 공식 구현 pytorch
shreyesss/hdrsplat pytorch

Tasks

NeRFNovel View Synthesis

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras

2025-08-13 · Chaoran Feng, Zhenyu Tang, Wangbo Yu, Yatian Pang 외 arxiv

Novel view synthesis and 4D reconstruction techniques predominantly rely on RGB cameras, thereby inheriting inherent limitations such as the dependence on adequate lighting, susceptibility to motion blur, and a limited d…

Dynamic ReconstructionNovel View Synthesis

Radiance Fields from Photons

2024-07-12 · Sacha Jungerman, Aryan Garg, Mohit Gupta

Neural radiance fields, or NeRFs, have become the de facto approach for high-quality view synthesis from a collection of images captured from multiple viewpoints. However, many issues remain when capturing images in-the-…

MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second

2025-07-14 · Chenguo Lin, YuChen Lin, Panwang Pan, Yifan Yu 외

We present MoVieS, a novel feed-forward model that synthesizes 4D dynamic novel views from monocular videos in one second. MoVieS represents dynamic 3D scenes using pixel-aligned grids of Gaussian primitives, explicitly …

Novel View SynthesisPoint TrackingScene Flow EstimationSemantic Segmentation

E2GS: Event Enhanced Gaussian Splatting

2024-06-21 · Hiroyuki Deguchi, Mana Masuda, Takuya Nakabayashi, Hideo Saito

Event cameras, known for their high dynamic range, absence of motion blur, and low energy usage, have recently found a wide range of applications thanks to these attributes. In the past few years, the field of event-base…

3D ReconstructionDeblurringImage DeblurringNeRF+1

NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images

2021-11-26 · CVPR 2022 1 · Ben Mildenhall, Peter Hedman, Ricardo Martin-Brualla, Pratul Srinivasan 외

Neural Radiance Fields (NeRF) is a technique for high quality novel view synthesis from a collection of posed input images. Like most view synthesis methods, NeRF uses tonemapped low dynamic range (LDR) as input; these i…

NeRFNovel View Synthesis