Search Results for author: Zhaoxin Fan

Found 26 papers, 11 papers with code

Idea-2-3D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs

1 code implementation5 Apr 2024 JunHao Chen, Xiang Li, Xiaojun Ye, Chao Li, Zhaoxin Fan, Hao Zhao

The definition of an IDEA is the composition of multimodal inputs including text, image, and 3D models.

Model Selection

Ultraman: Single Image 3D Human Reconstruction with Ultra Speed and Detail

no code implementations18 Mar 2024 Mingjin Chen, JunHao Chen, Xiaojun Ye, Huan-ang Gao, Xiaoxue Chen, Zhaoxin Fan, Hao Zhao

In this paper, we propose a new method called \emph{Ultraman} for fast reconstruction of textured 3D human models from a single image.

3D Human Reconstruction Texture Synthesis

AS-FIBA: Adaptive Selective Frequency-Injection for Backdoor Attack on Deep Face Restoration

no code implementations11 Mar 2024 Zhenbo Song, Wenhao Gao, Kaihao Zhang, Wenhan Luo, Zhaoxin Fan, Jianfeng Lu

Extensive experiments demonstrate the efficacy of the degradation objective on state-of-the-art face restoration models.

Backdoor Attack

Adversarial Purification and Fine-tuning for Robust UDC Image Restoration

no code implementations21 Feb 2024 Zhenbo Song, Zhenyuan Zhang, Kaihao Zhang, Wenhan Luo, Zhaoxin Fan, Jianfeng Lu

This study delves into the enhancement of Under-Display Camera (UDC) image restoration models, focusing on their robustness against adversarial attacks.

Image Restoration

SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis

1 code implementation29 Nov 2023 Ziqiao Peng, Wentao Hu, Yue Shi, Xiangyu Zhu, Xiaomei Zhang, Hao Zhao, Jun He, Hongyan Liu, Zhaoxin Fan

A lifelike talking head requires synchronized coordination of subject identity, lip movements, facial expressions, and head poses.

Talking Face Generation Talking Head Generation

BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval

no code implementations16 Oct 2023 Kaixing Yang, Xukun Zhou, Xulong Tang, Ran Diao, Hongyan Liu, Jun He, Zhaoxin Fan

Dance and music are closely related forms of expression, with mutual retrieval between dance videos and music being a fundamental task in various fields like education, art, and sports.

Contrastive Learning Retrieval

Multi-dimensional Fusion and Consistency for Semi-supervised Medical Image Segmentation

no code implementations12 Sep 2023 Yixing Lu, Zhaoxin Fan, Min Xu

In this paper, we introduce a novel semi-supervised learning framework tailored for medical image segmentation.

Image Segmentation Semantic Segmentation +1

D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field

1 code implementation ICCV 2023 Xueting Yang, Yihao Luo, Yuliang Xiu, Wei Wang, Hao Xu, Zhaoxin Fan

In this paper, we propose replacing the implicit value with an adaptive uncertainty distribution, to differentiate between points based on their distance to the surface.

SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces

1 code implementation19 Jun 2023 Ziqiao Peng, Yihao Luo, Yue Shi, Hao Xu, Xiangyu Zhu, Jun He, Hongyan Liu, Zhaoxin Fan

To enhance the visual accuracy of generated lip movement while reducing the dependence on labeled data, we propose a novel framework SelfTalk, by involving self-supervision in a cross-modals network system to learn 3D talking faces.

3D Face Animation Lip Reading

EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation

2 code implementations ICCV 2023 Ziqiao Peng, HaoYu Wu, Zhenbo Song, Hao Xu, Xiangyu Zhu, Jun He, Hongyan Liu, Zhaoxin Fan

Specifically, we introduce the emotion disentangling encoder (EDE) to disentangle the emotion and content in the speech by cross-reconstructed speech signals with different emotion labels.

3D Face Animation Disentanglement

SHLE: Devices Tracking and Depth Filtering for Stereo-based Height Limit Estimation

1 code implementation22 Dec 2022 Zhaoxin Fan, Kaixing Yang, Min Zhang, Zhenbo Song, Hongyan Liu, Jun He

In stage 1, a novel devices detection and tracking scheme is introduced, which accurately locate the height limit devices in the left or right image.

FuRPE: Learning Full-body Reconstruction from Part Experts

1 code implementation30 Nov 2022 Zhaoxin Fan, Yuqing Pan, Hao Xu, Zhenbo Song, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He

These novel elements of FuRPE not only serve to further refine the model but also to reduce potential biases that may arise from inaccuracies in pseudo labels, thereby optimizing the network's training process and enhancing the robustness of the model.

GIDP: Learning a Good Initialization and Inducing Descriptor Post-enhancing for Large-scale Place Recognition

no code implementations23 Sep 2022 Zhaoxin Fan, Zhenbo Song, Hongyan Liu, Jun He

Large-scale place recognition is a fundamental but challenging task, which plays an increasingly important role in autonomous driving and robotics.

Autonomous Driving

Human Pose Driven Object Effects Recommendation

no code implementations17 Sep 2022 Zhaoxin Fan, Fengxin Li, Hongyan Liu, Jun He, Xiaoyong Du

In this paper, we research the new topic of object effects recommendation in micro-video platforms, which is a challenging but important task for many practical applications such as advertisement insertion.


MonoSIM: Simulating Learning Behaviors of Heterogeneous Point Cloud Object Detectors for Monocular 3D Object Detection

1 code implementation19 Aug 2022 Han Sun, Zhaoxin Fan, Zhenbo Song, Zhicheng Wang, Kejian Wu, Jianfeng Lu

The insight behind introducing MonoSIM is that we propose to simulate the feature learning behaviors of a point cloud based detector for monocular detector during the training period.

Autonomous Driving Depth Estimation +4

Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion

no code implementations20 Apr 2022 Zhaoxin Fan, Yulin He, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He

Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important.

Point Cloud Completion

Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Image

no code implementations4 Apr 2022 Zhaoxin Fan, Zhenbo Song, Jian Xu, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He

Recently, RGBD-based category-level 6D object pose estimation has achieved promising improvement in performance, however, the requirement of depth information prohibits broader applications.

6D Pose Estimation using RGB Object

RPR-Net: A Point Cloud-based Rotation-aware Large Scale Place Recognition Network

no code implementations29 Aug 2021 Zhaoxin Fan, Zhenbo Song, Wenping Zhang, Hongyan Liu, Jun He, Xiaoyong Du

Third, we apply these kernels to previous point cloud features to generate new features, which is the well-known SO(3) mapping process.

Autonomous Driving Point Cloud Retrieval +2

Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview

no code implementations29 May 2021 Zhaoxin Fan, Yazhi Zhu, Yulin He, Qi Sun, Hongyan Liu, Jun He

Therefore, this study presents a comprehensive review of recent progress in object pose detection and tracking that belongs to the deep learning technical route.

Autonomous Driving Object +1

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