PMID- 37071518
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20230426
LR  - 20230426
IS  - 1941-0042 (Electronic)
IS  - 1057-7149 (Linking)
VI  - 32
DP  - 2023
TI  - Boosting Night-Time Scene Parsing With Learnable Frequency.
PG  - 2386-2398
LID - 10.1109/TIP.2023.3267044 [doi]
AB  - Night-Time Scene Parsing (NTSP) is essential to many vision applications, 
      especially for autonomous driving. Most of the existing methods are proposed for 
      day-time scene parsing. They rely on modeling pixel intensity-based spatial 
      contextual cues under even illumination. Hence, these methods do not perform well 
      in night-time scenes as such spatial contextual cues are buried in the 
      over-/under-exposed regions in night-time scenes. In this paper, we first conduct 
      an image frequency-based statistical experiment to interpret the day-time and 
      night-time scene discrepancies. We find that image frequency distributions differ 
      significantly between day-time and night-time scenes, and understanding such 
      frequency distributions is critical to NTSP problem. Based on this, we propose to 
      exploit the image frequency distributions for night-time scene parsing. First, we 
      propose a Learnable Frequency Encoder (LFE) to model the relationship between 
      different frequency coefficients to measure all frequency components dynamically. 
      Second, we propose a Spatial Frequency Fusion module (SFF) that fuses both 
      spatial and frequency information to guide the extraction of spatial context 
      features. Extensive experiments show that our method performs favorably against 
      the state-of-the-art methods on the NightCity, NightCity+ and BDD100K-night 
      datasets. In addition, we demonstrate that our method can be applied to existing 
      day-time scene parsing methods and boost their performance on night-time scenes. 
      The code is available at https://github.com/wangsen99/FDLNet.
FAU - Xie, Zhifeng
AU  - Xie Z
FAU - Wang, Sen
AU  - Wang S
FAU - Xu, Ke
AU  - Xu K
FAU - Zhang, Zhizhong
AU  - Zhang Z
FAU - Tan, Xin
AU  - Tan X
FAU - Xie, Yuan
AU  - Xie Y
FAU - Ma, Lizhuang
AU  - Ma L
LA  - eng
PT  - Journal Article
DEP - 20230425
PL  - United States
TA  - IEEE Trans Image Process
JT  - IEEE transactions on image processing : a publication of the IEEE Signal 
      Processing Society
JID - 9886191
SB  - IM
EDAT- 2023/04/19 06:00
MHDA- 2023/04/19 06:01
CRDT- 2023/04/18 12:33
PHST- 2023/04/19 06:01 [medline]
PHST- 2023/04/19 06:00 [pubmed]
PHST- 2023/04/18 12:33 [entrez]
AID - 10.1109/TIP.2023.3267044 [doi]
PST - ppublish
SO  - IEEE Trans Image Process. 2023;32:2386-2398. doi: 10.1109/TIP.2023.3267044. Epub 
      2023 Apr 25.