Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?
Citations
2,231 citations
725 citations
692 citations
Cites methods from "Bounding Boxes, Segmentations and O..."
...Top ranked methods on the KITTI benchmark typically involve the joint reasoning of geometry, rigid motion and segmentation [3, 51]....
[...]
386 citations
Cites background from "Bounding Boxes, Segmentations and O..."
...Scene understanding in 3D plays a principal role in designing effective real-world systems such as in urban autonomous driving [2, 10, 15] and robotics [17, 36]....
[...]
329 citations
Cites background from "Bounding Boxes, Segmentations and O..."
...Behl et al.[4] integrated the instance recognition cues into a CRF-based model for scene flow estimation....
[...]
References
[...]
14,824 citations
[...]
14,747 citations
"Bounding Boxes, Segmentations and O..." refers methods in this paper
...The network is trained by minimizing a robust and smooth Huber loss [11] using the Adam solver with a momentum of 0....
[...]
12,531 citations
11,283 citations
"Bounding Boxes, Segmentations and O..." refers background or methods in this paper
...With the advent of challenging realworld benchmarks, such as the KITTI 2012 [10] and KITTI...
[...]
...We pre-train the network using Pascal VOC and finetune it using 3200 coarse annotations of KITTI [10] provided by [5]....
[...]
...While these methods have demonstrated impressive performance on the challenging KITTI benchmark [10, 22], they fail to establish correspondences in textureless, reflective or fast-moving regions due to violations and ambiguities of the data term and weak prior assumptions....
[...]
10,161 citations
"Bounding Boxes, Segmentations and O..." refers methods in this paper
...We model our encoder-decoder network for 3D object coordinate prediction in Caffe [17]....
[...]