Yong-Jin Liu

papers

1,248

total citations

papers (22)

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild

ECCV 2022arXiv

citations

PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows

ECCV 2022arXiv

citations

Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos

CVPR 2023arXiv

citations

A Confidence-Based Iterative Solver of Depths and Surface Normals for Deep Multi-View Stereo

ICCV 2021arXiv

citations

Rectified Diffusion Guidance for Conditional Generation

CVPR 2025arXiv

citations

Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner

CVPR 2024arXiv

citations

SMaRt: Improving GANs with Score Matching Regularity

ICML 2024arXiv

citations

DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints

AAAI 2025arXiv

citations

StdGEN: Semantic-Decomposed 3D Character Generation from Single Images

CVPR 2025arXiv

citations

Weighted Poisson-disk Resampling on Large-Scale Point Clouds

AAAI 2025arXiv

citations

NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesis

ECCV 2024arXiv

citations

TeethGenerator: A two-stage framework for paired pre- and post-orthodontic 3D dental data generation

ICCV 2025arXiv

citations

Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation

AAAI 2024

citations

Audio-Driven Stylized Gesture Generation with Flow-Based Model

ECCV 2022

citations

SceneSketcher: Fine-Grained Image Retrieval with Scene Sketches

ECCV 2020

citations

Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping

CVPR 2020

citations

Multimodal Contrastive Learning for Cybersickness Recognition Using Brain Connectivity Graph Representation

ISMAR 2025

citations

Autoregressive Stylized Motion Synthesis With Generative Flow

CVPR 2021

citations

O2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model

AAAI 2024

citations

Yong-Jin Liu

papers (22)

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

ExpeL: LLM Agents Are Experiential Learners

Towards Better Generalization: Joint Depth-Pose Learning Without PoseNet

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild

PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows

Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos

A Confidence-Based Iterative Solver of Depths and Surface Normals for Deep Multi-View Stereo

Rectified Diffusion Guidance for Conditional Generation

Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner

SMaRt: Improving GANs with Score Matching Regularity

DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints

StdGEN: Semantic-Decomposed 3D Character Generation from Single Images

Weighted Poisson-disk Resampling on Large-Scale Point Clouds

NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesis

TeethGenerator: A two-stage framework for paired pre- and post-orthodontic 3D dental data generation

Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation

Audio-Driven Stylized Gesture Generation with Flow-Based Model

SceneSketcher: Fine-Grained Image Retrieval with Scene Sketches

Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping

Multimodal Contrastive Learning for Cybersickness Recognition Using Brain Connectivity Graph Representation

Autoregressive Stylized Motion Synthesis With Generative Flow

O2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model

papers (22)

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

ExpeL: LLM Agents Are Experiential Learners

Towards Better Generalization: Joint Depth-Pose Learning Without PoseNet

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild

PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows

Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos

A Confidence-Based Iterative Solver of Depths and Surface Normals for Deep Multi-View Stereo

Rectified Diffusion Guidance for Conditional Generation

Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner

SMaRt: Improving GANs with Score Matching Regularity

DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints

StdGEN: Semantic-Decomposed 3D Character Generation from Single Images

Weighted Poisson-disk Resampling on Large-Scale Point Clouds

NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesis

TeethGenerator: A two-stage framework for paired pre- and post-orthodontic 3D dental data generation

Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation

Audio-Driven Stylized Gesture Generation with Flow-Based Model

SceneSketcher: Fine-Grained Image Retrieval with Scene Sketches

Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping

Multimodal Contrastive Learning for Cybersickness Recognition Using Brain Connectivity Graph Representation

Autoregressive Stylized Motion Synthesis With Generative Flow

O2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model