activity
20192022
most citedOmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion

3 citations · 4 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV20223 cited

OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion

Yuyan Li, Yuliang Guo, Zhixin Yan +3

A well-known challenge in applying deep-learning methods to omnidirectional images is spherical distortion. In dense regression tasks such as depth estimation, where structural det…

cs.CV2022

PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation

Yuyan Li, Zhixin Yan, Ye Duan +1

Omnidirectional 3D information is essential for a wide range of applications such as Virtual Reality, Autonomous Driving, Robotics, etc. In this paper, we propose a novel, model-ag…

cs.CV2021

Fast Point Voxel Convolution Neural Network with Selective Feature Fusion for Point Cloud Semantic Segmentation

Xu Wang, Yuyan Li, Ye Duan

We present a novel lightweight convolutional neural network for point cloud analysis. In contrast to many current CNNs which increase receptive field by downsampling point cloud, o…

cs.CV2021

SPNet: Multi-Shell Kernel Convolution for Point Cloud Semantic Segmentation

Yuyan Li, Chuanmao Fan, Xu Wang +1

Feature encoding is essential for point cloud analysis. In this paper, we propose a novel point convolution operator named Shell Point Convolution (SPConv) for shape encoding and l…

cs.CV2019

The Semantic Mutex Watershed for Efficient Bottom-Up Semantic Instance Segmentation

Steffen Wolf, Yuyan Li, Constantin Pape +3

Semantic instance segmentation is the task of simultaneously partitioning an image into distinct segments while associating each pixel with a class label. In commonly used pipeline…

cs.CV20191 cited

RED-NET: A Recursive Encoder-Decoder Network for Edge Detection

Truc Le, Yuyan Li, Ye Duan

In this paper, we introduce RED-NET: A Recursive Encoder-Decoder Network with Skip-Connections for edge detection in natural images. The proposed network is a novel integration of…