no code implementations • ECCV 2020 • Yinda Zhang, Neal Wadhwa, Sergio Orts-Escolano, Christian Häne, Sean Fanello, Rahul Garg
Computational stereo has reached a high level of accuracy, but degrades in the presence of occlusions, repeated textures, and correspondence errors along edges.
no code implementations • 2 Apr 2024 • Di Qiu, yinda zhang, Thabo Beeler, Vladimir Tankovich, Christian Häne, Sean Fanello, Christoph Rhemann, Sergio Orts Escolano
We propose CHOSEN, a simple yet flexible, robust and effective multi-view depth refinement framework.
no code implementations • 17 Feb 2022 • David Li, yinda zhang, Christian Häne, Danhang Tang, Amitabh Varshney, Ruofei Du
Immersive maps such as Google Street View and Bing Streetside provide true-to-life views with a massive collection of panoramas.
8 code implementations • CVPR 2021 • Vladimir Tankovich, Christian Häne, yinda zhang, Adarsh Kowdle, Sean Fanello, Sofien Bouaziz
Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not explicitly build a volume and instead relies on a fast multi-resolution initialization step, differentiable 2D geometric propagation and warping mechanisms to infer disparity hypotheses.
Ranked #1 on Stereo Depth Estimation on KITTI2015
no code implementations • 31 Mar 2020 • Yinda Zhang, Neal Wadhwa, Sergio Orts-Escolano, Christian Häne, Sean Fanello, Rahul Garg
Computational stereo has reached a high level of accuracy, but degrades in the presence of occlusions, repeated textures, and correspondence errors along edges.
no code implementations • 8 Sep 2018 • Wei-cheng Kuo, Christian Häne, Esther Yuh, Pratik Mukherjee, Jitendra Malik
Deep learning for clinical applications is subject to stringent performance requirements, which raises a need for large labeled datasets.
no code implementations • 8 Jun 2018 • Wei-cheng Kuo, Christian Häne, Esther Yuh, Pratik Mukherjee, Jitendra Malik
This paper studies the problem of detecting and segmenting acute intracranial hemorrhage on head computed tomography (CT) scans.
1 code implementation • 31 Aug 2017 • Christian Häne, Lionel Heng, Gim Hee Lee, Friedrich Fraundorfer, Paul Furgale, Torsten Sattler, Marc Pollefeys
To minimize the number of cameras needed for surround perception, we utilize fisheye cameras.
1 code implementation • NeurIPS 2017 • Abhishek Kar, Christian Häne, Jitendra Malik
We thoroughly evaluate our approach on the ShapeNet dataset and demonstrate the benefits over classical approaches as well as recent learning based methods.
1 code implementation • 3 Apr 2017 • Christian Häne, Shubham Tulsiani, Jitendra Malik
A major limitation of such approaches is that they only predict a coarse resolution voxel grid, which does not capture the surface of the objects well.
no code implementations • 2 Feb 2015 • Ľubor Ladický, Christian Häne, Marc Pollefeys
In this paper we propose a method, which learns the matching function, that automatically finds the space of allowed changes in visual appearance, such as due to the motion blur, chromatic distortions, different colour calibration or seasonal changes.
no code implementations • 14 Aug 2013 • Christopher Zach, Christian Häne
The number of unknowns is O(LK) per pairwise clique in terms of the state space size $L$ and the number of linear segments K. This compares to an O(L^2) size complexity of the standard LP relaxation if the piecewise linear structure is ignored.