Search Results for author: Zhuo Su

Found 23 papers, 10 papers with code

RobustFusion: Human Volumetric Capture with Data-driven Visual Cues using a RGBD Camera

no code implementations ECCV 2020 Zhuo Su, Lan Xu, Zerong Zheng, Tao Yu, Yebin Liu, Lu Fang

To enable robust tracking, we embrace both the initial model and the various visual cues into a novel performance capture scheme with hybrid motion optimization and semantic volumetric fusion, which can successfully capture challenging human motions under the monocular setting without pre-scanned detailed template and owns the reinitialization ability to recover from tracking failures and the disappear-reoccur scenarios.

4D reconstruction

HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors

1 code implementation18 Jun 2024 Panwang Pan, Zhuo Su, Chenguo Lin, Zhen Fan, YongJie Zhang, Zeming Li, Tingting Shen, Yadong Mu, Yebin Liu

Despite recent advancements in high-fidelity human reconstruction techniques, the requirements for densely captured images or time-consuming per-instance optimization significantly hinder their applications in broader scenarios.

Novel View Synthesis

HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations

no code implementations CVPR 2024 Peng Dai, Yang Zhang, Tao Liu, Zhen Fan, Tianyuan Du, Zhuo Su, Xiaozheng Zheng, Zeming Li

It is especially challenging to achieve real-time human motion tracking on a standalone VR Head-Mounted Display (HMD) such as Meta Quest and PICO.


Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning

1 code implementation4 Mar 2024 Huali Xu, Li Liu, Shuaifeng Zhi, Shaojing Fu, Zhuo Su, Ming-Ming Cheng, Yongxiang Liu

For this reason, this paper explores a Source-Free CDFSL (SF-CDFSL) problem, in which CDFSL is addressed through the use of existing pretrained models instead of training a model with source data, avoiding accessing source data.

Contrastive Learning cross-domain few-shot learning

OHTA: One-shot Hand Avatar via Data-driven Implicit Priors

no code implementations CVPR 2024 Xiaozheng Zheng, Chao Wen, Zhuo Su, Zeran Xu, Zhaohu Li, Yang Zhao, Zhou Xue

In this paper, we delve into the creation of one-shot hand avatars, attaining high-fidelity and drivable hand representations swiftly from a single image.

Lightweight Pixel Difference Networks for Efficient Visual Representation Learning

1 code implementation1 Feb 2024 Zhuo Su, Jiehua Zhang, Longguang Wang, Hua Zhang, Zhen Liu, Matti Pietikäinen, Li Liu

With PDC and Bi-PDC, we further present two lightweight deep networks named \emph{Pixel Difference Networks (PiDiNet)} and \emph{Binary PiDiNet (Bi-PiDiNet)} respectively to learn highly efficient yet more accurate representations for visual tasks including edge detection and object recognition.

Edge Detection Object Recognition +1

Joint2Human: High-quality 3D Human Generation via Compact Spherical Embedding of 3D Joints

no code implementations CVPR 2024 Muxin Zhang, Qiao Feng, Zhuo Su, Chao Wen, Zhou Xue, Kun Li

In this work, we introduce Joint2Human, a novel method that leverages 2D diffusion models to generate detailed 3D human geometry directly, ensuring both global structure and local details.

3D Generation

HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting

no code implementations CVPR 2024 Yuheng Jiang, Zhehao Shen, Penghao Wang, Zhuo Su, Yu Hong, Yingliang Zhang, Jingyi Yu, Lan Xu

Then, we utilize a 4D Gaussian optimization scheme with adaptive spatial-temporal regularizers to effectively balance the non-rigid prior and Gaussian updating.

Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling

1 code implementation ICCV 2023 Xiaozheng Zheng, Zhuo Su, Chao Wen, Zhou Xue, Xiaojie Jin

To bridge the physical and virtual worlds for rapidly developed VR/AR applications, the ability to realistically drive 3D full-body avatars is of great significance.

Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution

1 code implementation13 Apr 2023 Zhuo Su, Jiehua Zhang, Tianpeng Liu, Zhen Liu, Shuanghui Zhang, Matti Pietikäinen, Li Liu

This paper proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) with the mechanism of grouped convolution.

Image Classification object-detection +1

Boosting Binary Neural Networks via Dynamic Thresholds Learning

no code implementations4 Nov 2022 Jiehua Zhang, Xueyang Zhang, Zhuo Su, Zitong Yu, Yanghe Feng, Xin Lu, Matti Pietikäinen, Li Liu

For ViTs, DyBinaryCCT presents the superiority of the convolutional embedding layer in fully binarized ViTs and achieves 56. 1% on the ImageNet dataset, which is nearly 9% higher than the baseline.


Learning Variational Motion Prior for Video-based Motion Capture

no code implementations27 Oct 2022 Xin Chen, Zhuo Su, Lingbo Yang, Pei Cheng, Lan Xu, Bin Fu, Gang Yu

To improve the generalization capacity of prior space, we propose a transformer-based variational autoencoder pretrained over marker-based 3D mocap data, with a novel style-mapping block to boost the generation quality.

Pose Estimation

SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation

1 code implementation13 Sep 2022 Zhuo Su, Max Welling, Matti Pietikäinen, Li Liu

Precisely, the presence of scalar features makes the major part of the network binarizable, while vector features serve to retain rich structural information and ensure SO(3) equivariance.

Autonomous Driving Binarization +1

Median Pixel Difference Convolutional Network for Robust Face Recognition

no code implementations30 May 2022 Jiehua Zhang, Zhuo Su, Li Liu

Face recognition is one of the most active tasks in computer vision and has been widely used in the real world.

Face Recognition Robust Face Recognition

Dynamic Binary Neural Network by learning channel-wise thresholds

no code implementations8 Oct 2021 Jiehua Zhang, Zhuo Su, Yanghe Feng, Xin Lu, Matti Pietikäinen, Li Liu

The experimental results prove that our method is an effective and straightforward way to reduce information loss and enhance performance of BNNs.

Pixel Difference Networks for Efficient Edge Detection

2 code implementations ICCV 2021 Zhuo Su, Wenzhe Liu, Zitong Yu, Dewen Hu, Qing Liao, Qi Tian, Matti Pietikäinen, Li Liu

A faster version of PiDiNet with less than 0. 1M parameters can still achieve comparable performance among state of the arts with 200 FPS.

Edge Detection

RobustFusion: Robust Volumetric Performance Reconstruction under Human-object Interactions from Monocular RGBD Stream

no code implementations30 Apr 2021 Zhuo Su, Lan Xu, Dawei Zhong, Zhong Li, Fan Deng, Shuxue Quan, Lu Fang

To fill this gap, in this paper, we propose RobustFusion, a robust volumetric performance reconstruction system for human-object interaction scenarios using only a single RGBD sensor, which combines various data-driven visual and interaction cues to handle the complex interaction patterns and severe occlusions.

4D reconstruction Disentanglement +5

FTBNN: Rethinking Non-linearity for 1-bit CNNs and Going Beyond

1 code implementation19 Oct 2020 Zhuo Su, Linpu Fang, Deke Guo, Dewen Hu, Matti Pietikäinen, Li Liu

Binary neural networks (BNNs), where both weights and activations are binarized into 1 bit, have been widely studied in recent years due to its great benefit of highly accelerated computation and substantially reduced memory footprint that appeal to the development of resource constrained devices.

Image Classification Quantization

Dynamic Group Convolution for Accelerating Convolutional Neural Networks

1 code implementation ECCV 2020 Zhuo Su, Linpu Fang, Wenxiong Kang, Dewen Hu, Matti Pietikäinen, Li Liu

In this paper, we propose dynamic group convolution (DGC) that adaptively selects which part of input channels to be connected within each group for individual samples on the fly.

Computational Efficiency Image Classification

Searching Central Difference Convolutional Networks for Face Anti-Spoofing

4 code implementations CVPR 2020 Zitong Yu, Chenxu Zhao, Zezheng Wang, Yunxiao Qin, Zhuo Su, Xiaobai Li, Feng Zhou, Guoying Zhao

Here we propose a novel frame level FAS method based on Central Difference Convolution (CDC), which is able to capture intrinsic detailed patterns via aggregating both intensity and gradient information.

Face Anti-Spoofing Face Recognition +1

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