Illumination Distillation Framework for Nighttime Person Re-Identification and A New Benchmark

• URL: http://arxiv.org/abs/2308.16486v1
• Date: Thu, 31 Aug 2023 06:45:56 GMT
• Title: Illumination Distillation Framework for Nighttime Person Re-Identification and A New Benchmark
• Authors: Andong Lu, Zhang Zhang, Yan Huang, Yifan Zhang, Chenglong Li, Jin Tang, and Liang Wang
• Abstract summary: This paper proposes an Illumination Distillation Framework (IDF) to address the low illumination challenge in nighttime person Re-ID. IDF consists of a master branch, an illumination enhancement branch, and an illumination distillation module. We build a real-world nighttime person Re-ID dataset, named Night600, which contains 600 identities.
• Score: 29.6321130075977
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Nighttime person Re-ID (person re-identification in the nighttime) is a very important and challenging task for visual surveillance but it has not been thoroughly investigated. Under the low illumination condition, the performance of person Re-ID methods usually sharply deteriorates. To address the low illumination challenge in nighttime person Re-ID, this paper proposes an Illumination Distillation Framework (IDF), which utilizes illumination enhancement and illumination distillation schemes to promote the learning of Re-ID models. Specifically, IDF consists of a master branch, an illumination enhancement branch, and an illumination distillation module. The master branch is used to extract the features from a nighttime image. The illumination enhancement branch first estimates an enhanced image from the nighttime image using a nonlinear curve mapping method and then extracts the enhanced features. However, nighttime and enhanced features usually contain data noise due to unstable lighting conditions and enhancement failures. To fully exploit the complementary benefits of nighttime and enhanced features while suppressing data noise, we propose an illumination distillation module. In particular, the illumination distillation module fuses the features from two branches through a bottleneck fusion model and then uses the fused features to guide the learning of both branches in a distillation manner. In addition, we build a real-world nighttime person Re-ID dataset, named Night600, which contains 600 identities captured from different viewpoints and nighttime illumination conditions under complex outdoor environments. Experimental results demonstrate that our IDF can achieve state-of-the-art performance on two nighttime person Re-ID datasets (i.e., Night600 and Knight ). We will release our code and dataset at https://github.com/Alexadlu/IDF.

Related papers

• Exploring Reliable Matching with Phase Enhancement for Night-time Semantic Segmentation [58.180226179087086]
  We propose a novel end-to-end optimized approach, named NightFormer, tailored for night-time semantic segmentation. Specifically, we design a pixel-level texture enhancement module to acquire texture-aware features hierarchically with phase enhancement and amplified attention. Our proposed method performs favorably against state-of-the-art night-time semantic segmentation methods.
  arXiv  Detail & Related papers  (2024-08-25T13:59:31Z)
• NocPlace: Nocturnal Visual Place Recognition via Generative and Inherited Knowledge Transfer [11.203135595002978]
  NocPlace embeds resilience against dazzling lights and extreme darkness in the global descriptor. NocPlace improves the performance of Eigenplaces by 7.6% on Tokyo 24/7 Night and 16.8% on SVOX Night.
  arXiv  Detail & Related papers  (2024-02-27T02:47:09Z)
• Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution [28.685126418090338]
  Existing nighttime dehazing methods often struggle with handling glow or low-light conditions. In this paper, we enhance the visibility from a single nighttime haze image by suppressing glow and enhancing low-light regions. Our method achieves a PSNR of 30.38dB, outperforming state-of-the-art methods by 13% on GTA5 nighttime haze dataset.
  arXiv  Detail & Related papers  (2023-08-03T12:58:23Z)
• From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement [22.565044107631696]
  Existing Low-Light Image Enhancement (LLIE) methods are primarily designed to improve brightness in dark regions, which suffer from severe degradation in nighttime images. These methods have limited exploration in another major visibility damage, the glow effects in real night scenes. We propose a new method for learning physical glow generation via multiple scattering estimation according to the Atmospheric Point Spread Function (APSF) The proposed method is based on zero-shot learning and does not rely on any paired or unpaired training data. Empirical evaluations demonstrate the effectiveness of the proposed method in both glow suppression and low-light enhancement tasks.
  arXiv  Detail & Related papers  (2023-07-31T15:51:15Z)
• Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement [11.13045179377011]
  We propose a novel semantic segmentation paradigm, i.e., disentangle then parse (DTP) DTP explicitly disentangles night-time images into light-invariant reflectance and light-specific illumination components. We show that DTP significantly outperforms state-of-the-art methods for night-time segmentation.
  arXiv  Detail & Related papers  (2023-07-18T15:46:21Z)
• Disentangled Contrastive Image Translation for Nighttime Surveillance [87.03178320662592]
  Nighttime surveillance suffers from degradation due to poor illumination and arduous human annotations. Existing methods rely on multi-spectral images to perceive objects in the dark, which are troubled by low resolution and color absence. We argue that the ultimate solution for nighttime surveillance is night-to-day translation, or Night2Day. This paper contributes a new surveillance dataset called NightSuR. It includes six scenes to support the study on nighttime surveillance.
  arXiv  Detail & Related papers  (2023-07-11T06:40:27Z)
• Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond [77.72043833102191]
  We introduce the first comprehensive nighttime flare removal dataset, consisting of 962 real-captured flare images (Flare-R) and 7,000 synthetic flares (Flare7K) Compared to Flare7K, Flare7K++ is particularly effective in eliminating complicated degradation around the light source, which is intractable by using synthetic flares alone. To address this issue, we additionally provide the annotations of light sources in Flare7K++ and propose a new end-to-end pipeline to preserve the light source while removing lens flares.
  arXiv  Detail & Related papers  (2023-06-07T08:27:44Z)
• Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Dark [57.85378202032541]
  Rain in the dark poses a significant challenge to deploying real-world applications such as autonomous driving, surveillance systems, and night photography. Existing low-light enhancement or deraining methods struggle to brighten low-light conditions and remove rain simultaneously. We introduce an end-to-end model called L$2$RIRNet, designed to manage both low-light enhancement and deraining in real-world settings.
  arXiv  Detail & Related papers  (2023-05-06T10:17:42Z)
• Flare7K: A Phenomenological Nighttime Flare Removal Dataset [83.38205781536578]
  We introduce Flare7K, the first nighttime flare removal dataset. It offers 5,000 scattering and 2,000 reflective flare images, consisting of 25 types of scattering flares and 10 types of reflective flares. With the paired data, we can train deep models to restore flare-corrupted images taken in the real world effectively.
  arXiv  Detail & Related papers  (2022-10-12T20:17:24Z)
• Nighttime Dehazing with a Synthetic Benchmark [147.21955799938115]
  We propose a novel synthetic method called 3R to simulate nighttime hazy images from daytime clear images. We generate realistic nighttime hazy images by sampling real-world light colors from a prior empirical distribution. Experiment results demonstrate their superiority over state-of-the-art methods in terms of both image quality and runtime.
  arXiv  Detail & Related papers  (2020-08-10T02:16:46Z)
• Illumination adaptive person reid based on teacher-student model and adversarial training [11.307571732296513]
  We propose a Two-Stream Network that can separate ReID features from lighting features to enhance ReID performance. Our algorithm outperforms other state-of-the-art works and particularly potent in handling images under extremely low light.
  arXiv  Detail & Related papers  (2020-02-05T03:49:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.