NTIRE 2022 Challenge on Night Photography Rendering

Ershov, Egor; Savchik, Alexey; Shepelev, Denis; Banić, Nikola; Brown, Michael S.; Timofte, Radu; Koščević, Karlo; Freeman, Michael R.; Tesalin, Vasily; Bocharov, Dmitry; Semenkov, Illya; Subašić, Marko; Lončarić, Sven; Terekhin, Arseniy P.; Liu, Shuai; Feng, Chaoyu; Wang, Hao; Zhu, Rong; Li, Yongqiang; Lei, Lei; Li, Zhihao; Yi, Si; Han, Ling-Hao; Wu, Ruiqi; Jin, Xin; Guo, Chunle; Kınlı, Furkan; Menteş, Sami; Özcan, Barış; Kıraç, Furkan; Zini, Simone; Rota, Claudio; Buzzelli, Marco; Bianco, Simone; Schettini, Raimondo; Li, Wei; Ma, Yipeng; Wang, Tao; Xu, Ruikang; Song, Fenglong; Chen, Wei‐Ting; Yang, Hao-Hsiang; Huang, Zhi-Kai; Chang, Hua-En; Kuo, Sy‐Yen; Liang, Zhexin; Zhou, Shangchen; Ran, Feng; Li, Chongyi; Chen, Xiangyu; Song, Binbin; Zhang, Shile; Liu, Lin; Wang, Zhendong; Ryu, Dohoon; Bae, Hyokyoung; Kwon, Tae‐Sung; Akalwadi, Nikhil; Joshi, Amogh; Mandi, Chinmayee; Malagi, Sampada; Uppin, Akash; Reddy, Sai Sudheer; Tabib, Ramesh Ashok; Patil, Ujwala; Mudenagudi, Uma

doi:10.1109/cvprw56347.2022.00135

Cited by 21 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Replacing the conventional signal-processing ISP with a neural one has been a topic of significant interest in the past few years, with many ideas being explored in terms of architecture and loss functions and several competitions being organized yearly [8], [15]- [18], [26]. With the growing emphasis on improving smartphone image quality, the first RAW-to-sRGB challenges in [16], [18] aimed to process lowquality RAW images from a smartphone camera to look like high-quality rendered images from a DSLR camera.…”

Section: Related Workmentioning

confidence: 99%

“…The two networks, Restore-Net and Enhance-Net, were first trained separately using an MAE reconstruction loss and later jointly finetuned using a combination of MAE and perceptual losses. Recently, the more complex task of processing RAW images of nighttime scenes to sRGB was considered in the night photography rendering challenge [8], [26]. Due to the unique lighting environment in nighttime scenes, white balance, tone curves, and photofinishing strategies vary significantly for nighttime rendering compared to daytime photography.…”

Section: Related Workmentioning

confidence: 99%

“…2 (D). In particular, the winner of the challenge in [8], DeepFlexISP [23], used a three-stage network structure breaking down the full ISP into a denoising network, a white-balance network, and a Bayer-to-sRGB network. There were also user-controllable parameters for denoising strength, color cast, and overall brightness.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Advocating Pixel-Level Authentication of Camera-Captured Images

Punnappurath,

Zhao,

Abdelhamed

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

The authenticity of digital images posted online and shared on social media is often questioned due to the ability of photo-editing software to alter image content and generative AI methods that can produce visually compelling deepfakes. Only images directly produced by cameras are deemed unaltered and beyond suspicion, as they have not undergone any modifications. However, there is a recent trend among camera manufacturers to integrate AI-based modules into the dedicated onboard hardware, specifically the image signal processor (ISP), responsible for processing the captured sensor image into the final saved image for users. Many of these AI modules utilize perceptual or generative losses during training, which can ''hallucinate'' image content. While this hallucinated content often manifests as small details and textures, there are instances where these regions unintentionally impact the interpretation of the entire image. This paper aims to bring attention to this issue and advocate for in-camera strategies to validate the authenticity of camera-captured images at a pixel level. We propose the creation of an "authenticity" mask that could be stored as additional metadata with each image. This information can be extracted and overlaid on the image to easily identify the hallucinated regions. Considering the widespread implications of image authenticity (e.g., in courtroom evidence, news broadcasts, and other media forms), we anticipate that authentication metadata will become a standard practice for any ISP utilizing AI.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Advocating Pixel-Level Authentication of Camera-Captured Images

Punnappurath,

Zhao,

Abdelhamed

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…This challenge is one of the NTIRE 2022 associated challenges on: spectral recovery [4], spectral demosaicing [3], perceptual image quality assessment [22], inpainting [63], night photography rendering [18], efficient super-resolution [46], learning the super-resolution space [56], super-resolution and quality enhancement of compressed video [78], high dynamic range [60], stereo super-resolution [71], burst super-resolution [7].…”

Section: Ntire 2022 Efficient Super-resolution Challengementioning

confidence: 99%

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

Li¹,

Zhang²,

Timofte³

et al. 2022

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

Self Cite

View full text Add to dashboard Cite

This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity),

show abstract

“…This challenge is one of the NTIRE 2022 associated challenges: spectral recovery [7], spectral demosaicing [6], perceptual image quality assessment [19], inpainting [40], night photography rendering [17], efficient super-resolution [31], learning the super-resolution space [34], super-resolution and quality enhancement of compressed video [49], high dynamic range [38], stereo super-resolution [45], burst super-resolution [8].…”

Section: Introductionmentioning

confidence: 99%

NTIRE 2022 Spectral Recovery Challenge and Data Set

Arad¹,

Timofte²,

Yahel³

et al. 2022

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

Self Cite

View full text Add to dashboard Cite

This paper reviews the third biennial challenge on spectral reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. This challenge presents the "ARAD 1K" data set: a new, larger-than-ever natural hyperspectral image data set containing 1,000 images. Challenge participants were required to recover hyperspectral information from synthetically generated JPEGcompressed RGB images simulating capture by a known calibrated camera, operating under partially known parameters, in a setting which includes acquisition noise. The challenge was attended by 241 teams, with 60 teams competing in the final testing phase, 12 of which provided detailed descriptions of their methodology which are included in this report. The performance of these submissions is reviewed and provided here as a gauge for the current stateof-the-art in spectral reconstruction from natural RGB images.

show abstract

NTIRE 2022 Challenge on Night Photography Rendering

Cited by 21 publications

References 47 publications

Advocating Pixel-Level Authentication of Camera-Captured Images

Advocating Pixel-Level Authentication of Camera-Captured Images

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

NTIRE 2022 Spectral Recovery Challenge and Data Set

Contact Info

Product

Resources

About