PMID- 34705644
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20211104
IS  - 1941-0042 (Electronic)
IS  - 1057-7149 (Linking)
VI  - 30
DP  - 2021
TI  - Night-Time Scene Parsing With a Large Real Dataset.
PG  - 9085-9098
LID - 10.1109/TIP.2021.3122004 [doi]
AB  - Although huge progress has been made on scene analysis in recent years, most 
      existing works assume the input images to be in day-time with good lighting 
      conditions. In this work, we aim to address the night-time scene parsing (NTSP) 
      problem, which has two main challenges: 1) labeled night-time data are scarce, 
      and 2) over- and under-exposures may co-occur in the input night-time images and 
      are not explicitly modeled in existing pipelines. To tackle the scarcity of 
      night-time data, we collect a novel labeled dataset, named NightCity, of 4,297 
      real night-time images with ground truth pixel-level semantic annotations. To our 
      knowledge, NightCity is the largest dataset for NTSP. In addition, we also 
      propose an exposure-aware framework to address the NTSP problem through 
      augmenting the segmentation process with explicitly learned exposure features. 
      Extensive experiments show that training on NightCity can significantly improve 
      NTSP performances and that our exposure-aware model outperforms the 
      state-of-the-art methods, yielding top performances on our dataset as well as 
      existing datasets.
FAU - Tan, Xin
AU  - Tan X
FAU - Xu, Ke
AU  - Xu K
FAU - Cao, Ying
AU  - Cao Y
FAU - Zhang, Yiheng
AU  - Zhang Y
FAU - Ma, Lizhuang
AU  - Ma L
FAU - Lau, Rynson W H
AU  - Lau RWH
LA  - eng
PT  - Journal Article
DEP - 20211103
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- 2021/10/28 06:00
MHDA- 2021/10/28 06:01
CRDT- 2021/10/27 17:19
PHST- 2021/10/28 06:00 [pubmed]
PHST- 2021/10/28 06:01 [medline]
PHST- 2021/10/27 17:19 [entrez]
AID - 10.1109/TIP.2021.3122004 [doi]
PST - ppublish
SO  - IEEE Trans Image Process. 2021;30:9085-9098. doi: 10.1109/TIP.2021.3122004. Epub 
      2021 Nov 3.