Low-Level Vision

Project Overview

We have worked on basic algorithmic building blocks that support visual data processing. Our algorithms have advanced the state of the art in optical flow estimation, visual odometry, bottom-up segmentation, intrinsic image decomposition, and other low-level vision problems.

Publications

Monocular Visual-Inertial Depth Estimation

Diana Wofk, René Ranftl, Matthias Müller, and Vladlen Koltun
International Conference on Robotics and Automation (ICRA), 2023

Shape from Polarization for Complex Scenes in the Wild

Chenyang Lei, Chenyang Qi, Jiaxin Xie, Na Fan, Vladlen Koltun, and Qifeng Chen
Computer Vision and Pattern Recognition (CVPR), 2022

High-dimensional Convolutional Networks for Geometric Pattern Recognition

Christopher Choy, Junha Lee, René Ranftl, Jaesik Park, and Vladlen Koltun
Computer Vision and Pattern Recognition (CVPR), 2020 (Selected for full oral presentation)

Does Computer Vision Matter for Action?

Brady Zhou, Philipp Krähenbühl, and Vladlen Koltun
Science Robotics, 4(30), 2019

Connecting the Dots: Learning Representations for Active Monocular Depth Estimation

Gernot Riegler, Yiyi Liao, Simon Donné, Vladlen Koltun, and Andreas Geiger
Computer Vision and Pattern Recognition (CVPR), 2019

Motion Perception in Reinforcement Learning with Dynamic Objects

Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun, and Thomas Brox
Conference on Robot Learning (CoRL), 2018

Deep Fundamental Matrix Estimation

René Ranftl and Vladlen Koltun
European Conference on Computer Vision (ECCV), 2018

Interactive Image Segmentation with Latent Diversity

Zhuwen Li, Qifeng Chen, and Vladlen Koltun
Computer Vision and Pattern Recognition (CVPR), 2018

Playing for Benchmarks

Stephan R. Richter, Zeeshan Hayder, and Vladlen Koltun
International Conference on Computer Vision (ICCV), 2017 (Selected for spotlight oral presentation)

Accurate Optical Flow via Direct Cost Volume Processing

Jia Xu, René Ranftl, and Vladlen Koltun
Computer Vision and Pattern Recognition (CVPR), 2017

Direct Sparse Odometry

Jakob Engel, Vladlen Koltun, and Daniel Cremers
IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(3), 2018

Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids

Qifeng Chen and Vladlen Koltun
Computer Vision and Pattern Recognition (CVPR), 2016 (Selected for full oral presentation)

Learning to Propose Objects

Philipp Krähenbühl and Vladlen Koltun
Computer Vision and Pattern Recognition (CVPR), 2015

Geodesic Object Proposals

Philipp Krähenbühl and Vladlen Koltun
European Conference on Computer Vision (ECCV), 2014 (Selected for full oral presentation)

Fast MRF Optimization with Application to Depth Reconstruction

Qifeng Chen and Vladlen Koltun
Computer Vision and Pattern Recognition (CVPR), 2014

A Simple Model for Intrinsic Image Decomposition with Depth Cues

Qifeng Chen and Vladlen Koltun
International Conference on Computer Vision (ICCV), 2013

Efficient Nonlocal Regularization for Optical Flow

Philipp Krähenbühl and Vladlen Koltun
European Conference on Computer Vision (ECCV), 2012