We present an interactive, robust and high quality method for fast shadow removal. To perform detection we use an on-the-fly learning approach guided by two rough user inputs for the pixels of the shadow and the lit area. From this we derive a fusion image that magnifies shadow boundary intensity change due to illumination variation. After detection, we perform shadow removal by registering the penumbra to a normalised frame which allows us to efficiently estimate non-uniform shadow illumination changes, resulting in accurate and robust removal. We also present the first reliable, validated and multi-scene category ground truth for shadow removal algorithms which overcomes limitations in existing data sets -- such as inconsistencies between shadow and shadow-free images and limited variations of shadows. Using our data, we perform the most thorough comparison of state of the art shadow removal methods to date. Our algorithm outperforms the state of the art, and we supply our code and evaluation data and scripts to encourage future open comparisons.
|Number of pages||11|
|Publication status||Published - 5 Sep 2014|
|Event||BMVC 2014 - Proceedings of the British Machine Vision Conference 2014 - Nottingham , UK United Kingdom|
Duration: 1 Sep 2014 → 5 Sep 2014
|Conference||BMVC 2014 - Proceedings of the British Machine Vision Conference 2014|
|Country/Territory||UK United Kingdom|
|Period||1/09/14 → 5/09/14|
FingerprintDive into the research topics of 'Interactive Shadow Removal and Ground Truth for Variable Scene Categories'. Together they form a unique fingerprint.
- Department of Computer Science - Professor
- EPSRC Centre for Doctoral Training in Statistical Applied Mathematics (SAMBa)
- Centre for the Analysis of Motion, Entertainment Research & Applications
- UKRI CDT in Accountable, Responsible and Transparent AI
- Centre for Autonomous Robotics (CENTAUR)
- Visual Computing
Person: Research & Teaching