![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Chapter and Conference Paper
Du2Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels
Computational stereo has reached a high level of accuracy, but degrades in the presence of occlusions, repeated textures, and correspondence errors along edges. We present a novel approach based on neural netw...
-
Chapter and Conference Paper
Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection
Deep learning for clinical applications is subject to stringent performance requirements, which raises a need for large labeled datasets. However, the enormous cost of labeling medical data makes this challeng...
-
Chapter and Conference Paper
Discretized Convex Relaxations for the Piecewise Smooth Mumford-Shah Model
The Mumford-Shah model for image formation is an important, but also difficult energy functional. In this work we focus on several approaches based on convex relaxation operating on a discretized image domain....
-
Chapter and Conference Paper
Semantic 3D Reconstruction of Heads
We present a novel approach that jointly reconstructs the geometry of a human head and semantically segments it into labels such as skin, hair and eyebrows. In order to get faithful reconstructions from data c...
-
Chapter and Conference Paper
Multi-body Depth-Map Fusion with Non-intersection Constraints
Depthmap fusion is the problem of computing dense 3D reconstructions from a set of depthmaps. Whereas this problem has received a lot of attention for purely rigid scenes, there is remarkably little prior work...