Improving sub-pixel correspondence through upsampling

Many fundamental computer vision problems, including optical flow estimation and stereo matching, involve the key step of computing dense color matching among pixels. In this paper, we show that by merely upsampling, we can improve sub-pixel correspondence estimation. In addition, we identify the regularization bias problem and explore its relationship to image resolution. We propose a general upsampling framework to compute sub-pixel color matching for different computer vision problems. Various experiments were performed on motion estimation and stereo matching data. We are able to reduce errors by up to 30%, which would otherwise be very difficult to achieve through other conventional optimization methods.

► We improve sub-pixel matching for various vision problems merely through upsampling.
► It has been thoroughly discussed how scale changes affect data and regularization terms.
► We fuse results in different scales for effective error suppression.
► Effectiveness has been borne out by stereo matching and optical flow estimation.