Instance Segmentation in the Dark

Linwei Chen, Ying Fu, Kaixuan Wei, Dezhi Zheng, Felix Heide

Research output: Contribution to journalArticlepeer-review

5 Scopus citations


Existing instance segmentation techniques are primarily tailored for high-visibility inputs, but their performance significantly deteriorates in extremely low-light environments. In this work, we take a deep look at instance segmentation in the dark and introduce several techniques that substantially boost the low-light inference accuracy. The proposed method is motivated by the observation that noise in low-light images introduces high-frequency disturbances to the feature maps of neural networks, thereby significantly degrading performance. To suppress this “feature noise”, we propose a novel learning method that relies on an adaptive weighted downsampling layer, a smooth-oriented convolutional block, and disturbance suppression learning. These components effectively reduce feature noise during downsampling and convolution operations, enabling the model to learn disturbance-invariant features. Furthermore, we discover that high-bit-depth RAW images can better preserve richer scene information in low-light conditions compared to typical camera sRGB outputs, thus supporting the use of RAW-input algorithms. Our analysis indicates that high bit-depth can be critical for low-light instance segmentation. To mitigate the scarcity of annotated RAW datasets, we leverage a low-light RAW synthetic pipeline to generate realistic low-light data. In addition, to facilitate further research in this direction, we capture a real-world low-light instance segmentation dataset comprising over two thousand paired low/normal-light images with instance-level pixel-wise annotations. Remarkably, without any image preprocessing, we achieve satisfactory performance on instance segmentation in very low light (4% AP higher than state-of-the-art competitors), meanwhile opening new opportunities for future research. Our code and dataset are publicly available to the community (

Original languageEnglish (US)
Pages (from-to)2198-2218
Number of pages21
JournalInternational Journal of Computer Vision
Issue number8
StatePublished - Aug 2023

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


  • Feature denoising
  • Instance segmentation
  • Low-light image dataset
  • Object detection


Dive into the research topics of 'Instance Segmentation in the Dark'. Together they form a unique fingerprint.

Cite this