Zhaoxin Fan

papers

457

total citations

papers (12)

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

ECCV 2022arXiv

citations

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

ICCV 2023arXiv

citations

CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction

ICCV 2025arXiv

citations

DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations

CVPR 2025arXiv

citations

JTD-UAV: MLLM-Enhanced Joint Tracking and Description Framework for Anti-UAV Systems

CVPR 2025

citations

MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing

CVPR 2025arXiv

citations

Moderating the Generalization of Score-based Generative Model

ICCV 2025arXiv

citations

Everything2Motion: Synchronizing Diverse Inputs via a Unified Framework for Human Motion Synthesis

AAAI 2024

citations

Robust Single Image Reflection Removal Against Adversarial Attacks

CVPR 2023

citations

Zhaoxin Fan

papers (12)

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

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

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers

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

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

CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction

DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations

JTD-UAV: MLLM-Enhanced Joint Tracking and Description Framework for Anti-UAV Systems

MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing

Moderating the Generalization of Score-based Generative Model

Everything2Motion: Synchronizing Diverse Inputs via a Unified Framework for Human Motion Synthesis

Robust Single Image Reflection Removal Against Adversarial Attacks

papers (12)

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

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

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers

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

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

CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction

DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations

JTD-UAV: MLLM-Enhanced Joint Tracking and Description Framework for Anti-UAV Systems

MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing

Moderating the Generalization of Score-based Generative Model

Everything2Motion: Synchronizing Diverse Inputs via a Unified Framework for Human Motion Synthesis

Robust Single Image Reflection Removal Against Adversarial Attacks