Visual Computing

We propose a novel object- and scene-based semantic fusion network and representation.

We propose a recurrent decision tree framework that can directly incorporate temporal consistency into a data-driven predictor, as well as a learning algorithm that can efficiently learn such temporally smooth models.

We present a novel approach to video segmentation using multiple object proposals.

We propose a new approach based on finding latent Path Patterns in both real and simulated data in order to analyze and compare them.

We propose a system for painting large-scale murals of arbitrary input photographs.

In this paper, we introduce a technique that preserves the appearance of heterogeneous elasticity textures mapped on deforming surfaces by calculating dense, content-aware parameterisation warps in realtime.

In this paper, we present a novel approach to author vegetation cover of large natural scenes.

We present an efficient algorithm to automatically segment a static foreground object from highly cluttered background in light fields.

In this paper, we present a set of experiments in which we explore some factors that contribute to the perception of cloth, to determine how efficiency could be improved without sacrificing realism.

In this work we propose ‘mean time between failures’ as a viable summary of solution quality - especially when the goal is to follow objects for as long as possible.