Publications

Li X., Han K., Li S. & Prisacariu V. (2020) Dual-Resolution Correspondence Networks. arXiv pre-print. (Project page)

Li S., Han K., Costain T.W., Howard-Jenkins H., & Prisacariu V. (2020) Correspondence Networks with Adaptive Neighbourhood Consensus. In CVPR. (Project page) (Source codes released)

Wang Z., Li S., H. Howard-Jenkins, Prisacariu V. & Chen M. (2019) FlowNet3D++: Geometric Losses for Deep Scene Flow Estimation. In WACV.

Balntas V. Li S. & Prisacariu V. (2018) RelocNet: Continuous Metric Learning Relocalisation Using Neural Nets. In ECCV. (Project page)

Howard-Jenkins H., Li S. & Prisacariu V. (2018) Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts. In ACCV.

Li, S., Handa, A., Zhang, Y. & Calway, A. (2016) HDRFusion: HDR SLAM using a low-cost auto-exposure RGB-D sensor. In 3DV. (Source codes released) (Dataset)

Li, S., & Calway, A. (2016). Absolute pose estimation using multiple forms of correspondences from RGB-D frames. In ICRA. (Source codes released)

Li, S., & Calway, A. (2015). RGBD Relocalisation Using Pairwise Geometry and Concise Key Point Sets. In ICRA. (Source codes updated)

Wong, K.-Y. K., Dirk, S., & Li, S. (2008). Recovering Light Directions and Camera Poses from a Single Sphere. In ECCV.

Li, S., Wong, K.-Y. K., & Dirk, S. (2008). Using Illumination Estimated from Silhouettes to Carve Surface Details on Visual Hull. In BMVC.