Search Results for author: Hujun Bao

Found 32 papers, 22 papers with code

CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation

1 code implementation13 Sep 2021 Yunfan Shao, Zhichao Geng, Yitao Liu, Junqi Dai, Fei Yang, Li Zhe, Hujun Bao, Xipeng Qiu

In this paper, we take the advantage of previous pre-trained models (PTMs) and propose a novel Chinese Pre-trained Unbalanced Transformer (CPT).

Denoising Language Modelling +2

Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering

no code implementations ICCV 2021 Bangbang Yang, yinda zhang, Yinghao Xu, Yijin Li, Han Zhou, Hujun Bao, Guofeng Zhang, Zhaopeng Cui

In this paper, we present a novel neural scene rendering system, which learns an object-compositional neural radiance field and produces realistic rendering with editing capability for a clustered and real-world scene.

Neural Rendering Novel View Synthesis

DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization

1 code implementation ICCV 2021 Cheng Zhang, Zhaopeng Cui, Cai Chen, Shuaicheng Liu, Bing Zeng, Hujun Bao, yinda zhang

Panorama images have a much larger field-of-view thus naturally encode enriched scene context information compared to standard perspective images, which however is not well exploited in the previous scene understanding methods.

Scene Understanding

MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis

no code implementations13 Jul 2021 Haocheng Ren, Hao Zhang, Jia Zheng, Jiaxiang Zheng, Rui Tang, Rui Wang, Hujun Bao

With the rapid development of data-driven techniques, data has played an essential role in various computer vision tasks.

Image Generation

Attention-guided Temporally Coherent Video Object Matting

1 code implementation24 May 2021 Yunke Zhang, Chi Wang, Miaomiao Cui, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Hujun Bao, QiXing Huang, Weiwei Xu

Experimental results show that our method can generate high-quality alpha mattes for various videos featuring appearance change, occlusion, and fast motion.

Image Matting Semantic Segmentation +3

VS-Net: Voting with Segmentation for Visual Localization

1 code implementation CVPR 2021 Zhaoyang Huang, Han Zhou, Yijin Li, Bangbang Yang, Yan Xu, Xiaowei Zhou, Hujun Bao, Guofeng Zhang, Hongsheng Li

To address this problem, we propose a novel visual localization framework that establishes 2D-to-3D correspondences between the query image and the 3D map with a series of learnable scene-specific landmarks.

Semantic Segmentation Visual Localization

Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies

no code implementations ICCV 2021 Sida Peng, Junting Dong, Qianqian Wang, Shangzhan Zhang, Qing Shuai, Xiaowei Zhou, Hujun Bao

Moreover, the learned blend weight fields can be combined with input skeletal motions to generate new deformation fields to animate the human model.

StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision

no code implementations CVPR 2021 Yang Hong, Juyong Zhang, Boyi Jiang, Yudong Guo, Ligang Liu, Hujun Bao

In this paper, we propose StereoPIFu, which integrates the geometric constraints of stereo vision with implicit function representation of PIFu, to recover the 3D shape of the clothed human from a pair of low-cost rectified images.

Reconstructing 3D Human Pose by Watching Humans in the Mirror

1 code implementation CVPR 2021 Qi Fang, Qing Shuai, Junting Dong, Hujun Bao, Xiaowei Zhou

In this paper, we introduce the new task of reconstructing 3D human pose from a single image in which we can see the person and the person's image through a mirror.

3D Pose Estimation

AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis

1 code implementation ICCV 2021 Yudong Guo, Keyu Chen, Sen Liang, Yong-Jin Liu, Hujun Bao, Juyong Zhang

Generating high-fidelity talking head video by fitting with the input audio sequence is a challenging problem that receives considerable attentions recently.

You Don't Only Look Once: Constructing Spatial-Temporal Memory for Integrated 3D Object Detection and Tracking

no code implementations ICCV 2021 Jiaming Sun, Yiming Xie, Siyu Zhang, Linghao Chen, Guofeng Zhang, Hujun Bao, Xiaowei Zhou

In this work, we propose a novel system for integrated 3D object detection and tracking, which uses a dynamic object occupancy map and previous object states as spatial-temporal memory to assist object detection in future frames.

3D Object Detection Object Proposal Generation

Graph-Based Asynchronous Event Processing for Rapid Object Recognition

no code implementations ICCV 2021 Yijin Li, Han Zhou, Bangbang Yang, Ye Zhang, Zhaopeng Cui, Hujun Bao, Guofeng Zhang

Different from traditional video cameras, event cameras capture asynchronous events stream in which each event encodes pixel location, trigger time, and the polarity of the brightness changes.

graph construction Object Recognition

Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans

2 code implementations CVPR 2021 Sida Peng, Yuanqing Zhang, Yinghao Xu, Qianqian Wang, Qing Shuai, Hujun Bao, Xiaowei Zhou

To this end, we propose Neural Body, a new human body representation which assumes that the learned neural representations at different frames share the same set of latent codes anchored to a deformable mesh, so that the observations across frames can be naturally integrated.

Novel View Synthesis Representation Learning

Location-aware Single Image Reflection Removal

1 code implementation ICCV 2021 Zheng Dong, Ke Xu, Yin Yang, Hujun Bao, Weiwei Xu, Rynson W. H. Lau

It is beneficial to strong reflection detection and substantially improves the quality of reflection removal results.

Reflection Removal

Recurrent Multi-view Alignment Network for Unsupervised Surface Registration

1 code implementation CVPR 2021 Wanquan Feng, Juyong Zhang, Hongrui Cai, Haofei Xu, Junhui Hou, Hujun Bao

Learning non-rigid registration in an end-to-end manner is challenging due to the inherent high degrees of freedom and the lack of labeled training data.

Deformable Object Manipulation Neural Rendering +1

SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks

no code implementations19 Oct 2020 Yan Xu, Zhaoyang Huang, Kwan-Yee Lin, Xinge Zhu, Jianping Shi, Hujun Bao, Guofeng Zhang, Hongsheng Li

To suit our network to self-supervised learning, we design several novel loss functions that utilize the inherent properties of LiDAR point clouds.

Self-Supervised Learning

Motion Capture from Internet Videos

2 code implementations ECCV 2020 Junting Dong, Qing Shuai, Yuanqing Zhang, Xian Liu, Xiaowei Zhou, Hujun Bao

Therefore, we propose to capture human motion by jointly analyzing these Internet videos instead of using single videos separately.

Motion Capture Pose Estimation

BCNet: Learning Body and Cloth Shape from A Single Image

1 code implementation ECCV 2020 Boyi Jiang, Juyong Zhang, Yang Hong, Jinhao Luo, Ligang Liu, Hujun Bao

In this paper, we consider the problem to automatically reconstruct garment and body shapes from a single near-front view RGB image.

Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose

1 code implementation24 Feb 2020 Ran Yi, Zipeng Ye, Juyong Zhang, Hujun Bao, Yong-Jin Liu

In this paper, we address this problem by proposing a deep neural network model that takes an audio signal A of a source person and a very short video V of a target person as input, and outputs a synthesized high-quality talking face video with personalized head pose (making use of the visual information in V), expression and lip synchronization (by considering both A and V).

3D Face Animation Video Generation

Deep Snake for Real-Time Instance Segmentation

1 code implementation CVPR 2020 Sida Peng, Wen Jiang, Huaijin Pi, Xiuli Li, Hujun Bao, Xiaowei Zhou

Based on deep snake, we develop a two-stage pipeline for instance segmentation: initial contour proposal and contour deformation, which can handle errors in object localization.

Object Localization Real-time Instance Segmentation +2

GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs

1 code implementation NeurIPS 2019 Yuan Liu, Zehong Shen, Zhixuan Lin, Sida Peng, Hujun Bao, Xiaowei Zhou

Instead of feature pooling, we use group convolutions to exploit underlying structures of the extracted features on the group, resulting in descriptors that are both discriminative and provably invariant to the group of transformations.

Pose Estimation

Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints

no code implementations ICCV 2019 Yan Xu, Xinge Zhu, Jianping Shi, Guofeng Zhang, Hujun Bao, Hongsheng Li

Most of existing methods directly train a network to learn a mapping from sparse depth inputs to dense depth maps, which has difficulties in utilizing the 3D geometric constraints and handling the practical sensor noises.

Autonomous Driving Depth Completion

PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation

1 code implementation CVPR 2019 Sida Peng, Yu-An Liu, Qi-Xing Huang, Hujun Bao, Xiaowei Zhou

We further create a Truncation LINEMOD dataset to validate the robustness of our approach against truncation.

 Ranked #1 on 6D Pose Estimation using RGB on YCB-Video (Mean AUC metric)

6D Pose Estimation using RGB

ICE-BA: Incremental, Consistent and Efficient Bundle Adjustment for Visual-Inertial SLAM

1 code implementation CVPR 2018 Hao-Min Liu, Mingyu Chen, Guofeng Zhang, Hujun Bao, Yingze Bao

However, jointly using visual and inertial measurements to optimize SLAM objective functions is a problem of high computational complexity.

Pose Estimation

Robust Keyframe-based Dense SLAM with an RGB-D Camera

9 code implementations14 Nov 2017 Hao-Min Liu, Chen Li, Guojun Chen, Guofeng Zhang, Michael Kaess, Hujun Bao

In this paper, we present RKD-SLAM, a robust keyframe-based dense SLAM approach for an RGB-D camera that can robustly handle fast motion and dense loop closure, and run without time limitation in a moderate size scene.

ENFT: Efficient Non-Consecutive Feature Tracking for Robust Structure-from-Motion

3 code implementations27 Oct 2015 Guofeng Zhang, Hao-Min Liu, Zilong Dong, Jiaya Jia, Tien-Tsin Wong, Hujun Bao

Our framework consists of steps of solving the feature `dropout' problem when indistinctive structures, noise or large image distortion exists, and of rapidly recognizing and joining common features located in different subsequences.

Structure from Motion

Cannot find the paper you are looking for? You can Submit a new open access paper.