Computer Vision Laboratory (CVL)

Welcome to the Computer Vision Laboratory (CVL), part of the Department of Electrical engineering at Linköping University.

Autonoma system datorseendePhoto: Göran Billeson

The field of computer vision has its roots in the modeling of the human
visual system (HVS); an extremely challenging task that generations of
researchers have attempted with limited success. Vision is a very
natural capability and it is commonly accepted that about 80% of what
we perceive is vision-based. The highly intuitive nature of the HVS
makes it difficult for us to understand the myriad of problems
associated with computer vision, in contrast to sophisticated analytic
tasks such as playing chess.

Thus computer vision became a widely underestimated scientific problem,
maybe one of the most underestimated problems of the past decades. Many
AI researchers believed that the real challenges were symbolic and
analytic problems and visual perception was just a simple sub-problem,
to be dealt with in a summer project, which obviously failed. The truth
is that computers are better than humans at playing chess since Deep
Blue, but first now computers are, thanks to modern machine learning,
superior to humans on generic vision tasks.

The research at the Computer Vision Laboratory (CVL) has a strong focus
on theory and methods, which are applied in application domains where
technical systems are supposed to coexist with – and therefore predict
actions of – humans, e.g. regarding self-driving cars sharing road
space and interacting with humans. Other addressed application domains
are monitoring of greenhouse gases, sustainable forestry, and
monitoring of animals on the individual level.

CVL's research topics cover a wide range of problems within machine
learning for computer vision and robot perception:

  • Continuous-time modeling of 3D motion
  • Estimation of pose and 3D structure
  • Few-shot and weakly supervised learning
  • Geometric deep learning
  • Human and animal motion analysis
  • Medical imaging
  • Quantum machine learning
  • Reinforcement learning
  • Remote sensing
  • Semi- supervised and incremental learning
  • Scene flow estimation
  • Uncertainty representation
  • Video and semantic segmentation
  • Vision for action


Courses given by the Division of Computer Vision Laboratory


Master Thesis Projects in Computer Vision


Follow CVL on social media

Twitter @CvlIsy


Research within WASP Computer Vision Laboratory

Other research collaborations


ELLIIT Joint Autonomous Systems Lab in Linköping and Lund showcasing autonomous robot.

The University Board on Study Visit to Visionen

In December 2023, the university board visited the Department of Electrical Engineering (ISY). In the research arena Visionen, examples were presented highlighting Linköping University's crucial role in technological and societal development.

The supercomputer Berzelius photographed with fisheye lens.

Swedish AI research gets more muscle

The supercomputer Berzelius was inaugurated in the spring of 2021, and was then Sweden's fastest supercomputer for AI. Yet, more power is needed to meet the needs of Swedish AI research.

Successful premiere for ISY's PhD Workshop

For the first time the Department of Electrical Engineering organized an all-day conference dedicated solely to the department's PhD-students. Afterwards the director of PhD studies, Mark Vesterbacka, was more than satisfied when he summed up the day

Portrait of Michael Felsberg with closed eyes.

Human vision – a challenge for AI

Achieving diversity in human vision is one of the major challenges for AI research. In the vast majority of cases, we are better than machines at understanding the world around us. But machines are catching up – slowly but surely.

Person with hoodie sitting behind computer in dark room.

AI: Helping criminal investigators find digital evidence

Cyberattacks are an increasing threat to society. So, for crime investigators, digital evidence is becoming more important in the hunt for criminals. And the technology exists – not least at Linköping University, where AI is an area of excellence.

Facial recognition

Facial recognition used in more and more ways

Research into facial recognition has been under way for a long time, but has really taken off in recent years. “The technology is beginning to be used in more and more contexts”, says Jörgen Ahlberg, researcher in computer vision.

Latest publications


Long Li, Junwei Han, Nian Liu, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Khan (2024) Robust Perception and Precise Segmentation for Scribble-Supervised RGB-D Saliency Detection IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 46, p. 479-496 Continue to DOI
Neelu Madan, Nicolae-Catalin Ristea, Radu Tudor Ionescu, Kamal Nasrollahi, Fahad Khan, Thomas B. Moeslund, Mubarak Shah (2024) Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 46, p. 525-542 Continue to DOI
Wafa Alghallabi, Akshay Dudhane, Waqas Zamir, Salman Khan, Fahad Khan (2024) Accelerated MRI Reconstruction via Dynamic Deformable Alignment Based Transformer MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2023, PT I, p. 104-114 Continue to DOI
Jyoti Kini, Fahad Khan, Salman Khan, Mubarak Shah (2024) CT-VOS: Cutout prediction and tagging for self-supervised video object segmentation Computer Vision and Image Understanding, Vol. 238, Article 103860 Continue to DOI


Akshita Gupta, Sanath Narayan, Salman Khan, Fahad Khan, Ling Shao, Joost van de Weijer (2023) Generative Multi-Label Zero-Shot Learning IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, p. 14611-14624 Continue to DOI

Staff at the Computer Vision Laboratory

About the Department