Author name cluster

Chenye Guan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

AAAI Conference 2020 Conference Paper

AutoRemover: Automatic Object Removal for Autonomous Driving Videos

Rong Zhang
Wei Li
Peng Wang
Chenye Guan
Jin Fang
Yuhang Song
Jinhui Yu
Baoquan Chen

Motivated by the need for photo-realistic simulation in autonomous driving, in this paper we present a video inpainting algorithm AutoRemover, designed speciﬁcally for generating street-view videos without any moving objects. In our setup we have two challenges: the ﬁrst is the shadow, shadows are usually unlabeled but tightly coupled with the moving objects. The second is the large ego-motion in the videos. To deal with shadows, we build up an autonomous driving shadow dataset and design a deep neural network to detect shadows automatically. To deal with large ego-motion, we take advantage of the multi-source data, in particular the 3D data, in autonomous driving. More speciﬁcally, the geometric relationship between frames is incorporated into an inpainting deep neural network to produce high-quality structurally consistent video output. Experiments show that our method outperforms other state-of-the-art (SOTA) object removal algorithms, reducing the RMSE by over 19%.

PDF Details

AAAI Conference 2020 Conference Paper

CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion

Xinjing Cheng
Peng Wang
Chenye Guan
Ruigang Yang

Depth Completion deals with the problem of converting a sparse depth map to a dense one, given the corresponding color image. Convolutional spatial propagation network (CSPN) is one of the state-of-the-art (SoTA) methods of depth completion, which recovers structural details of the scene. In this paper, we propose CSPN++, which further improves its effectiveness and efﬁciency by learning adaptive convolutional kernel sizes and the number of iterations for the propagation, thus the context and computational resource needed at each pixel could be dynamically assigned upon requests. Speciﬁcally, we formulate the learning of the two hyper-parameters as an architecture selection problem where various conﬁgurations of kernel sizes and numbers of iterations are ﬁrst deﬁned, and then a set of soft weighting parameters are trained to either properly assemble or select from the pre-deﬁned conﬁgurations at each pixel. In our experiments, we ﬁnd weighted assembling can lead to signiﬁcant accuracy improvements, which we referred to as ”contextaware CSPN”, while weighted selection, ”resource-aware CSPN” can reduce the computational resource signiﬁcantly with similar or better accuracy. Besides, the resource needed for CSPN++ can be adjusted w. r. t. the computational budget automatically. Finally, to avoid the side effects of noise or inaccurate sparse depths, we embed a gated network inside CSPN++, which further improves the performance. We demonstrate the effectiveness of CSPN++ on the KITTI depth completion benchmark, where it signiﬁcantly improves over CSPN and other SoTA methods 1.

PDF Details

ICRA Conference 2020 Conference Paper

Instance Segmentation of LiDAR Point Clouds

Feihu Zhang
Chenye Guan
Jin Fang
Song Bai 0001
Ruigang Yang
Philip H. S. Torr
Victor Adrian Prisacariu

We propose a robust baseline method for instance segmentation which are specially designed for large-scale outdoor LiDAR point clouds. Our method includes a novel dense feature encoding technique, allowing the localization and segmentation of small, far-away objects, a simple but effective solution for single-shot instance prediction and effective strategies for handling severe class imbalances. Since there is no public dataset for the study of LiDAR instance segmentation, we also build a new publicly available LiDAR point cloud dataset to include both precise 3D bounding box and point-wise labels for instance segmentation, while still being about 3~20 times as large as other existing LiDAR datasets. The dataset will be published at https://github.com/feihuzhang/LiDARSeg.

Details

ICRA Conference 2020 Conference Paper

Omnidirectional Depth Extension Networks

Xinjing Cheng
Peng Wang 0001
Yanqi Zhou
Chenye Guan
Ruigang Yang

Omnidirectional 360° camera proliferates rapidly for autonomous robots since it significantly enhances the perception ability by widening the field of view (FoV). However, corresponding 360° depth sensors, which are also critical for the perception system, are still difficult or expensive to have. In this paper, we propose a low-cost 3D sensing system that combines an omnidirectional camera with a calibrated projective depth camera, where the depth from the limited FoV can be automatically extended to the rest of recorded omnidirectional image. To accurately recover the missing depths, we design an omnidirectional depth extension convolutional neural network (ODE-CNN), in which a spherical feature transform layer (SFTL) is embedded at the end of feature encoding layers, and a deformable convolutional spatial propagation network (D-CSPN) is appended at the end of feature decoding layers. The former re-samples the neighborhood of each pixel in the omnidirectional coordination to the projective coordination, which reduce the difficulty of feature learning, and the later automatically finds a proper context to well align the structures in the estimated depths via CNN w. r. t. the reference image, which significantly improves the visual quality. Finally, we demonstrate the effectiveness of proposed ODE-CNN over the popular 360D dataset, and show that ODE-CNN significantly outperforms (relatively 33% reduction in depth error) other state-of-the-art (SoTA) methods.

Details