Proceedings ArticleDOI
Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?
Aseem Behl,Omid Hosseini Jafari,Siva Karthik Mustikovela,Hassan Abu Alhaija,Carsten Rother,Andreas Geiger +5 more
- pp 2593-2602
TLDR
The importance of recognition granularity is investigated, from coarse 2D bounding box estimates over 2D instance segmentations to fine-grained 3D object part predictions, and it is observed that the instance segmentation cue is by far strongest, in the authors' setting.Abstract:
Existing methods for 3D scene flow estimation often fail in the presence of large displacement or local ambiguities, e.g., at texture-less or reflective surfaces. However, these challenges are omnipresent in dynamic road scenes, which is the focus of this work. Our main contribution is to overcome these 3D motion estimation problems by exploiting recognition. In particular, we investigate the importance of recognition granularity, from coarse 2D bounding box estimates over 2D instance segmentations to fine-grained 3D object part predictions. We compute these cues using CNNs trained on a newly annotated dataset of stereo images and integrate them into a CRF-based model for robust 3D scene flow estimation - an approach we term Instance Scene Flow. We analyze the importance of each recognition cue in an ablation study and observe that the instance segmentation cue is by far strongest, in our setting. We demonstrate the effectiveness of our method on the challenging KITTI 2015 scene flow benchmark where we achieve state-of-the-art performance at the time of submission.read more
Citations
More filters
Book ChapterDOI
SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and Selection
TL;DR: In this article , the authors propose a novel approach to estimate scene dynamics in form of a segmentation into independently moving rigid objects and their SE(3)-motions on two consecutive stereo or RGB-D images.
Posted Content
Fast Hierarchical Depth Map Computation from Stereo.
Vinay Kaushik,Brejesh Lall +1 more
TL;DR: This paper introduces a novel multi-scale-hierarchical block-matching approach using a pyramidal variant of depth and cost functions which drastically improves the results of standard block matching stereo techniques while preserving the low memory footprint and further reducing the complexity ofstandard block matching.
Journal ArticleDOI
Unsupervised Learning Optical Flow in Multi-frame Dynamic Environment Using Temporal Dynamic Modeling
TL;DR: In this article , a spatial-temporal dual recurrent block based on the predictive coding structure is introduced to feed the previous high-level motion prior to the current optical flow estimator.
Journal ArticleDOI
Further Improving Weakly-supervised Object Localization via Causal Knowledge Distillation
TL;DR: Zhang et al. as mentioned in this paper propose a casual knowledge distillation method, dubbed KD-CI-CAM, to address the co-occurrence context confounder problem via causal intervention, which explores the causalities among image features, contexts, and categories to eliminate the biased object context entanglement in the class activation maps.
Posted Content
MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene FlowEstimation with Monocular Images
Runfa Li,Truong Q. Nguyen +1 more
TL;DR: MonoPLFlowNet as mentioned in this paper is the first work to estimate both depth and 3D scene flow in real scale using only two consecutive monocular images as input, which is comparable to LiDAR.
References
More filters
Proceedings ArticleDOI
Fast R-CNN
TL;DR: Fast R-CNN as discussed by the authors proposes a Fast Region-based Convolutional Network method for object detection, which employs several innovations to improve training and testing speed while also increasing detection accuracy and achieves a higher mAP on PASCAL VOC 2012.
Posted Content
Fast R-CNN
TL;DR: This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection that builds on previous work to efficiently classify object proposals using deep convolutional networks.
Posted Content
Caffe: Convolutional Architecture for Fast Feature Embedding
Yangqing Jia,Evan Shelhamer,Jeff Donahue,Sergey Karayev,Jonathan Long,Ross Girshick,Sergio Guadarrama,Trevor Darrell +7 more
TL;DR: Caffe as discussed by the authors is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.
Proceedings ArticleDOI
Are we ready for autonomous driving? The KITTI vision benchmark suite
TL;DR: The autonomous driving platform is used to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection, revealing that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world.
Proceedings ArticleDOI
Caffe: Convolutional Architecture for Fast Feature Embedding
Yangqing Jia,Evan Shelhamer,Jeff Donahue,Sergey Karayev,Jonathan Long,Ross Girshick,Sergio Guadarrama,Trevor Darrell +7 more
TL;DR: Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.