189 citations · 359 across the 29 of their papers we have counts for
9 papers · 1 filter
HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation
Xiaoyang Lyu, Liang Liu, Mengmeng Wang +5
Self-supervised learning shows great potential in monoculardepth estimation, using image sequences as the only source ofsupervision. Although people try to use the high-resolutioni…
FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completion
Lina Liu, Xibin Song, Xiaoyang Lyu +4
Depth completion aims to recover a dense depth map from a sparse depth map with the corresponding color image as input. Recent approaches mainly formulate depth completion as a one…
APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment
Jiangning Zhang, Xianfang Zeng, Chao Xu +3
Audio-guided face reenactment aims to generate a photorealistic face that has matched facial expression with the input audio. However, current methods can only reenact a special pe…
Hierarchical and Efficient Learning for Person Re-Identification
Jiangning Zhang, Liang Liu, Chao Xu +1
Recent works in the person re-identification task mainly focus on the model accuracy while ignore factors related to the efficiency, e.g. model size and latency, which are critical…
APB2Face: Audio-guided face reenactment with auxiliary pose and blink signals
Jiangning Zhang, Liang Liu, Zhucun Xue +1
Audio-guided face reenactment aims at generating photorealistic faces using audio information while maintaining the same facial movement as when speaking to a real person. However,…
Extended Feature Pyramid Network for Small Object Detection
Chunfang Deng, Mengmeng Wang, Liang Liu +1
Small object detection remains an unsolved challenge because it is hard to extract information of small objects with only a few pixels. While scale-level corresponding detection in…
A Learning Framework for n-bit Quantized Neural Networks toward FPGAs
Jun Chen, Liang Liu, Yong Liu +1
The quantized neural network (QNN) is an efficient approach for network compression and can be widely used in the implementation of FPGAs. This paper proposes a novel learning fram…
Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose
Xianfang Zeng, Yusu Pan, Mengmeng Wang +2
Recent works have shown how realistic talking face images can be obtained under the supervision of geometry guidance, e.g., facial landmark or boundary. To alleviate the demand for…
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation
Liang Liu, Jiangning Zhang, Ruifei He +7
Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods. However, the objective of…