Google Inc.

Waymo LLC

Pengchong Jin

Quoc V Le

Peyman Milanfar

Feng Yang

Xiaodan Song

Mingxing Tan

Golnaz Ghiasi

Tsung-Yi Lin

Yinxiao Li

Yi Shen

Yue Shen

Xianzhi Du

Yin Cui

Martin Nikoltchev

Guan Sun

The described aspects and implementations enable online lane estimation and tracking in autonomous vehicle and driver assistance applications. In one implementation, disclosed is a method and a system to perform the method that includes receiving perception data indicative of driving lanes and reference objects in a driving environment of a vehicle, identifying target destinations corresponding to the driving lanes, determining candidate driving paths connecting a starting location with one of the target destinations, selecting a target driving path from the candidate driving paths based on geometric properties of each candidate driving path and a spatial relationship of a respective candidate driving path to the reference objects, and causing a motion of the vehicle to be modified based on the target driving path.

Online lane estimation and tracking in autonomous vehicle and driving assistance applications

Example aspects of the present disclosure are directed to systems and methods which feature a machine-learned video super-resolution (VSR) model which has been trained using a bi-directional training approach. In particular, the present disclosure provides a compression-informed (e.g., compression-aware) super-resolution model that can perform well on real-world videos with different levels of compression. Specifically, example models described herein can include three modules to robustly restore the missing information caused by video compression. First, a bi-directional recurrent module can be used to reduce the accumulated warping error from the random locations of the intra-frame from compressed video frames. Second, a detail-aware flow estimation module can be added to enable recovery of high resolution (HR) flow from compressed low resolution (LR) frames. Finally, a Laplacian enhancement module can add high-frequency information to the warped HR frames washed out by video encoding.

Compression-informed video super-resolution

A computer-implemented method of generating scale-permuted models can generate models having improved accuracy and reduced evaluation computational requirements. The method can include defining, by a computing system including one or more computing devices, a search space including a plurality of candidate permutations of a plurality of candidate feature blocks, each of the plurality of candidate feature blocks having a respective scale. The method can include performing, by the computing system, a plurality of search iterations by a search algorithm to select a scale-permuted model from the search space, the scale-permuted model based at least in part on a candidate permutation of the plurality of candidate permutations.

Scale-permuted machine learning architecture

Growing community of inventors

Mountain View, CA, United States of America

Pengchong Jin