3D Datasets and Benchmarks

Institute Homepage

Institute Homepage Sign In

Back

Research Overview

3D Reconstruction

Depth Fusion using Successive Reprojections

3D Shape Completion

Deep Marching Cubes

Deep, Probabilistic and Semantic 3D Reconstruction

Learning Deep Representations of 3D

3D Datasets and Benchmarks

Sparsity Invariant CNNs

Efficient volumetric inference with OctNet

Motion Estimation and Scene Understanding

SphereNet

Unsupervised Learning of Flow with Occlusions

Slow Flow

Global Localization and Affordance Learning

Object Scene Flow

Deep Discrete Flow

Generative Models and Image Synthesis

Convergence and Stability of GAN training

Geometric Image Synthesis

Autonomous Vision Members Publications

3D Datasets and Benchmarks

Access to 3D datasets and benchmarks is crucial for driving progress in the field. Beyond our popular KITTI dataset, we have therefore proposed novel large-scale datasets for single-image depth prediction and depth map completion [], as well as two-view and multi-view 3D reconstruction in indoor and outdoor environments [] (ETH3D).

Members

Autonomous Vision, Perceiving Systems

Andreas Geiger

Guest Scientist

Publications

Autonomous Vision Conference Paper Sparsity Invariant CNNs Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A. International Conference on 3D Vision (3DV) 2017, International Conference on 3D Vision (3DV), October 2017 () pdf suppmat BibTeX

Autonomous Vision Conference Paper A Multi-View Stereo Benchmark with High-Resolution Images and Multi-Camera Videos Schöps, T., Schönberger, J. L., Galliani, S., Sattler, T., Schindler, K., Pollefeys, M., Geiger, A. In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 () pdf suppmat Project Page BibTeX