NeRF--: Neural Radiance Fields Without Known Camera Parameters

Wang, Zirui; Wu, Shangzhe; Xie, Weidi; Chen, Min; Prisacariu, Victor Adrian

doi:10.48550/arxiv.2102.07064

Cited by 97 publications

(131 citation statements)

References 56 publications

Supporting

Mentioning

131

Contrasting

Order By: Relevance

“…Our method is also dependent on COLMAP's [42] robustness for computing camera poses, preventing us from capturing scenes below a certain light level. This could potentially be addressed by jointly optimizing RawNeRF and the input camera poses [33,46]. Finally, despite its robustness to noise, RawNeRF cannot be considered a general purpose denoiser as it cannot handle scene motion and requires orders of magnitude more computation than a feed-forward network.…”

Section: Discussionmentioning

confidence: 99%

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

Mildenhall¹,

Hedman²,

Martin-Brualla³

et al. 2021

Preprint

View full text Add to dashboard Cite

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 images have been processed by a lossy camera pipeline that smooths detail, clips highlights, and distorts the simple noise distribution of raw sensor data. We modify NeRF to instead train directly on linear raw images, preserving the scene's full dynamic range. By rendering raw output images from the resulting NeRF, we can perform novel high dynamic range (HDR) view synthesis tasks. In addition to changing the camera viewpoint, we can manipulate focus, exposure, and tonemapping after the fact. Although a single raw image appears significantly more noisy than a postprocessed one, we show that NeRF is highly robust to the zeromean distribution of raw noise. When optimized over many noisy raw inputs (25-200), NeRF produces a scene representation so accurate that its rendered novel views outperform dedicated single and multi-image deep raw denoisers run on the same wide baseline input images. As a result, our method, which we call RawNeRF, can reconstruct scenes from extremely noisy images captured in near-darkness.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Mildenhall¹,

Hedman²,

Martin-Brualla³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A few recent papers [1,3,8,23,44] attempt to predict scene-level geometry with RGB-(D) inputs, but they all assume given camera poses. Another set of works [17,51,59] tackle the problem of camera pose optimization, but they need a rather long optimization process, which is not suitable for real-time applications.…”

Section: Related Workmentioning

confidence: 99%

NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Zhu¹,

Peng²,

Larsson³

et al. 2021

Preprint

View full text Add to dashboard Cite

Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce oversmoothed scene reconstructions and have difficulty scaling up to large scenes. These limitations are mainly due to their simple fully-connected network architecture that does not incorporate local information in the observations. In this paper, we present NICE-SLAM, a dense SLAM system that incorporates multi-level local information by introducing a hierarchical scene representation. Optimizing this representation with pre-trained geometric priors enables detailed reconstruction on large indoor scenes. Compared to recent neural implicit SLAM systems, our approach is more scalable, efficient, and robust. Experiments on five challenging datasets demonstrate competitive results of NICE-SLAM in both mapping and tracking quality. Project page: https:// pengsongyou.github.io/ nice-slam.

show abstract

“…Neural Radiance Fields Recent advancements (Mildenhall et al 2020;Hedman et al 2021;Jain, Tancik, and Abbeel 2021;Srinivasan et al 2021;Yu et al 2021;Lindell, Martel, and Wetzstein 2021) in the area of novel view synthesis have been accomplished by employing the NeRF. The seminal work (Mildenhall et al 2020) has proven the effectiveness of volume rendering with NeRF, and later studies (Hedman et al 2021;Wang et al 2021;Zhang et al 2020) proposed further improvements over the original NeRF. While some NeRF studies enhance the original NeRF in terms of both quality and efficiency, our work is more related to generative NeRF methods, which have attracted attention recently.…”

Section: Related Workmentioning

confidence: 99%