Single-Image Real-Time Rain Removal Based on Depth-Guided Non-Local Features

Hu, Xiaowei; Zhu, Lei; Wang, Tianyu; Fu, Chi‐Wing; Heng, Pheng‐Ann

doi:10.1109/tip.2020.3048625

Cited by 44 publications

(61 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…8. Alhough Hu et al [47] can handle fog, it is still challenging to remove rain streaks. In contrast, our method can handle rain streaks affected by fog in the real rain images because the proposed memory-based method with BSW loss captured real-world rain streaks well.…”

Section: ) Results On Real-world Datamentioning

confidence: 99%

“…3) Analysis on Rain Image with Fog: For further analysis, we analyzed whether the proposed method could estimate rain streaks even with fog. We also compared with state of the art methods including Hu et al [47], which proposed a depth-guided attention mechanism to remove rain and fog simultaneously. Fig.…”

Section: ) Results On Real-world Datamentioning

confidence: 99%

“…In this section, we demonstrate the results of comprehensive experiments conducted to evaluate the performance of the proposed method, including comparisons with several state of the art single-image de-raining methods that include JCAS [24], DDN [8], DID [9], NLEDN [14], RESCAN [45], PReNet [16], JORDER-E [10], SIRR [25], SPANET [12], Cho et al [6], Hu et al [47], Syn2Real [26], RCDNet [18], MPRNet [19], and MOSS [27]. We used public code or pre-trained models provided by the authors to produce the de-raining results.…”

Section: A Experimental Setupmentioning

confidence: 99%

“…Hu et al [47] SPANet [12] SIRR [25] Syn2Real [26] Ours Input Hu et al [47] JORDER-E [10] RCDNet [18] MOSS [27] Ours Fig. 8.…”

Section: Inputmentioning

confidence: 99%

“…Yang et al [13] designed fractal band learning network based on frequency band recovery. Hu et al [46], [47] proposed a depth-guided attention mechanism to remove rain and fog. Yasarla et al [60] proposed an image quality-based method that learns the quality or distortion level of each patch in the rain image.…”

Section: Related Work a Single Image De-rainingmentioning

confidence: 99%

See 4 more Smart Citations

Single Image Deraining Using Time-Lapse Data

Jaehoon

Kim

Min

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

This paper addresses the problem of single image de-raining, that is, the task of recovering clean and rain-free background scenes from a single image obscured by a rainy artifact. Although recent advances adopt real-world time-lapse data to overcome the need for paired rain-clean images, they are limited to fully exploit the time-lapse data. The main cause is that, in terms of network architectures, they could not capture long-term rain streak information in the time-lapse data during training owing to the lack of memory components. To address this problem, we propose a novel network architecture based on a memory network that explicitly helps to capture long-term rain streak information in the time-lapse data. Our network comprises the encoder-decoder networks and a memory network. The features extracted from the encoder are read and updated in the memory network that contains several memory items to store rain streak-aware feature representations. With the read/update operation, the memory network retrieves relevant memory items in terms of the queries, enabling the memory items to represent the various rain streaks included in the time-lapse data. To boost the discriminative power of memory features, we also present a novel background selective whitening (BSW) loss for capturing only rain streak information in the memory network by erasing the background information. Experimental results on standard benchmarks demonstrate the effectiveness and superiority of our approach.

show abstract

Section: ) Results On Real-world Datamentioning

confidence: 99%

Section: ) Results On Real-world Datamentioning

confidence: 99%