papers

Publications (52)

cs.CV2023

FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis

Feng Liang, Bichen Wu, Jialiang Wang +8

Diffusion models have transformed the image-to-image (I2I) synthesis and are now permeating into videos. However, the advancement of video-to-video (V2V) synthesis has been hampere…

cs.CV2017

Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions

Bichen Wu, Alvin Wan, Xiangyu Yue +6

Neural networks rely on convolutions to aggregate spatial information. However, spatial convolutions are expensive in terms of model size and computation, both of which grow quadra…

cs.CV2018

Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search

Bichen Wu, Yanghan Wang, Peizhao Zhang +3

Recent work in network quantization has substantially reduced the time and space complexity of neural network inference, enabling their deployment on embedded and mobile devices wi…

cs.CV2018

SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud

Bichen Wu, Xuanyu Zhou, Sicheng Zhao +2

Earlier work demonstrates the promise of deep-learning-based approaches for point cloud segmentation; however, these approaches need to be improved to be practically useful. To thi…

cs.SD2020

FBWave: Efficient and Scalable Neural Vocoders for Streaming Text-To-Speech on the Edge

Bichen Wu, Qing He, Peizhao Zhang +3

Nowadays more and more applications can benefit from edge-based text-to-speech (TTS). However, most existing TTS models are too computationally expensive and are not flexible enoug…

cs.CV2021

Unbiased Teacher for Semi-Supervised Object Detection

Yen-Cheng Liu, Chih-Yao Ma, Zijian He +6

Semi-supervised learning, i.e., training networks with both labeled and unlabeled data, has made significant progress recently. However, existing works have primarily focused on im…