HDR-NeRF: High Dynamic Range Neural Radiance Fields

Huang, Xin; Zhang, Qi; Feng, Yan; Li, Hongdong; Wang, Xuan; Wang, Qing

doi:10.1109/cvpr52688.2022.01785

Cited by 48 publications

(27 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural Implicit-based SLAM. Neural implicit representations [65] have shown great performance in many different tasks, including object-level reconstruction reconstruction [28,4,40,41,26,36,69], scene completion [42,24,17], novel view synthesis [29,44,72,31,64], etc. In terms of SLAM-related applications, some works [70,23,61,6,1,8] try to jointly optimize a neural radiance field and camera poses, but they are only applicable to small objects or small camera movements.…”

Section: Related Workmentioning

confidence: 99%

NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Zhu

Peng

Larsson

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

200

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Zhu

Peng

Larsson

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

200

View full text Add to dashboard Cite

show abstract

“…We then sample 64 more points in total via hierarchical sampling similar to [48]. We train without mask supervision, so we sample an additional 32 points along each ray and use them to learn a separate NeRF++ [55] model of the object background.…”

Section: Training Detailsmentioning

confidence: 99%

HR-NeuS: Recovering High-Frequency Surface Geometry via Neural Implicit Surfaces

Liang¹,

Deng²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Recent advances in neural implicit surfaces for multiview 3D reconstruction primarily focus on improving largescale surface reconstruction accuracy, but often produce over-smoothed geometries that lack fine surface details. To address this, we present High-Resolution NeuS (HR-NeuS), a novel neural implicit surface reconstruction method that recovers high-frequency surface geometry while maintaining large-scale reconstruction accuracy. We achieve this by utilizing (i) multi-resolution hash grid encoding rather than positional encoding at high frequencies, which boosts our model's expressiveness of local geometry details; (ii) a coarse-to-fine algorithmic framework that selectively applies surface regularization to coarse geometry without smoothing away fine details; (iii) a coarse-to-fine grid annealing strategy to train the network. We demonstrate through experiments on DTU and BlendedMVS datasets that our approach produces 3D geometries that are qualitatively more detailed and quantitatively of similar accuracy compared to previous approaches.

show abstract

“…Neural Radiance Fields (NeRF) ] is an implicit MLP-based model that maps 5D vectors-3D coordinates plus 2D viewing directions-to opacity and color values, computed by fitting the model to a set of training views. NeRF++ [Zhang et al 2020b]tries to solve the ambiguity problem of image reconstruction in NeRF, and present a novel spatial parameterization scheme. PixelNeRF [Yu et al 2021] can be achieved with fewer images.…”

Section: View Rendermentioning

confidence: 99%

Optical Aberrations Correction in Postprocessing Using Imaging Simulation

et al. 2021

View full text Add to dashboard Cite

As the popularity of mobile photography continues to grow, considerable effort is being invested in the reconstruction of degraded images. Due to the spatial variation in optical aberrations, which cannot be avoided during the lens design process, recent commercial cameras have shifted some of these correction tasks from optical design to postprocessing systems. However, without engaging with the optical parameters, these systems only achieve limited correction for aberrations. In this work, we propose a practical method for recovering the degradation caused by optical aberrations. Specifically, we establish an imaging simulation system based on our proposed optical point spread function model. Given the optical parameters of the camera, it generates the imaging results of these specific devices. To perform the restoration, we design a spatial-adaptive network model on synthetic data pairs generated by the imaging simulation system, eliminating the overhead of capturing training data by a large amount of shooting and registration. Moreover, we comprehensively evaluate the proposed method in simulations and experimentally with a customized digital-single-lens-reflex camera lens and HUAWEI HONOR 20, respectively. The experiments demonstrate that our solution successfully removes spatially variant blur and color dispersion. When compared with the state-of-the-art deblur methods, the proposed approach achieves better results with a lower computational overhead. Moreover, the reconstruction technique does not introduce artificial texture and is convenient to transfer to current commercial cameras. Project Page: https://github.com/TanGeeGo/ImagingSimulation .

show abstract

HDR-NeRF: High Dynamic Range Neural Radiance Fields

Cited by 48 publications

References 48 publications

NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

HR-NeuS: Recovering High-Frequency Surface Geometry via Neural Implicit Surfaces

Optical Aberrations Correction in Postprocessing Using Imaging Simulation

Contact Info

Product

Resources

About