Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
The Cityscapes Dataset for Semantic Urban Scene Understanding
- Marius Cordts, Mohamed Omran, B. Schiele
- Computer Science, Environmental ScienceIEEE Conference on Computer Vision and Pattern…
- 6 April 2016
This work introduces Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling, and exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity.
A Database and Evaluation Methodology for Optical Flow
- S. Baker, Daniel Scharstein, J. P. Lewis, S. Roth, Michael J. Black, R. Szeliski
- Computer ScienceIEEE 11th International Conference on Computer…
- 26 December 2007
This paper proposes a new set of benchmarks and evaluation methods for the next generation of optical flow algorithms and analyzes the results obtained to date to draw a large number of conclusions.
MOT16: A Benchmark for Multi-Object Tracking
A new release of the MOTChallenge benchmark, which focuses on multiple people tracking, and offers a significant increase in the number of labeled boxes, but also provides multiple object classes beside pedestrians and the level of visibility for every single object of interest.
Playing for Data: Ground Truth from Computer Games
It is shown that associations between image patches can be reconstructed from the communication between the game and the graphics hardware, which enables rapid propagation of semantic labels within and across images synthesized by the game, with no access to the source code or the content.
Secrets of optical flow estimation and their principles
- Deqing Sun, S. Roth, Michael J. Black
- Computer ScienceIEEE Computer Society Conference on Computer…
- 13 June 2010
It is discovered that “classical” flow formulations perform surprisingly well when combined with modern optimization and implementation techniques, and while median filtering of intermediate flow fields during optimization is a key to recent performance gains, it leads to higher energy solutions.
Fields of Experts: a framework for learning image priors
A framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks, developed using a Products-of-Experts framework.
Fields of Experts
The approach provides a practical method for learning high-order Markov random field models with potential functions that extend over large pixel neighborhoods with non-linear functions of many linear filter responses.
Benchmarking Denoising Algorithms with Real Photographs
This work develops a methodology for benchmarking denoising techniques on real photographs, and captures pairs of images with different ISO values and appropriately adjusted exposure times, where the nearly noise-free low-ISO image serves as reference.
Shrinkage Fields for Effective Image Restoration
This work proposes shrinkage fields, a random field-based architecture that combines the image model and the optimization algorithm in a single unit, and demonstrates state-of-the-art restoration results with high levels of computational efficiency, and significant speedup potential through inherent parallelism.
MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
With MOTChallenge, the work toward a novel multiple object tracking benchmark aimed to address issues of standardization, and the way toward a unified evaluation framework for a more meaningful quantification of multi-target tracking is described.