Songcen Xu

papers

1,642

total citations

papers (25)

CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation

ECCV 2022arXiv

297

citations

DualPoseNet: Category-Level 6D Object Pose and Size Estimation Using Dual Pose Network With Refined Learning of Pose Consistency

ICCV 2021arXiv

159

citations

Multiple Instance Active Learning for Object Detection

CVPR 2021arXiv

150

citations

AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning

CVPR 2023arXiv

citations

Renovating Parsing R-CNN for Accurate Multiple Human Parsing

ECCV 2020arXiv

citations

Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network

ICCV 2023arXiv

citations

Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images

AAAI 2024arXiv

citations

DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior

CVPR 2024arXiv

citations

Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model

CVPR 2024arXiv

citations

BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models

CVPR 2024arXiv

citations

MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections

ECCV 2024arXiv

citations

Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images

ICCV 2023arXiv

citations

Few-Shot Learning With Visual Distribution Calibration and Cross-Modal Distribution Alignment

CVPR 2023arXiv

citations

Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution

CVPR 2024arXiv

citations

MagicEraser: Erasing Any Objects via Semantics-Aware Control

ECCV 2024arXiv

citations

TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields

ICLR 2024arXiv

citations

Semantics-aware Motion Retargeting with Vision-Language Models

CVPR 2024arXiv

citations

CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval

CVPR 2023

citations

Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the Wild

NEURIPS 2023

citations

HiVLP: Hierarchical Interactive Video-Language Pre-Training

ICCV 2023

citations

PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval

ICCV 2023

citations

Co-Speech Gesture Synthesis by Reinforcement Learning With Contrastive Pre-Trained Rewards

CVPR 2023

citations

Songcen Xu

papers (25)

CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation

Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE

VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction

Instance Segmentation in 3D Scenes Using Semantic Superpoint Tree Networks

DualPoseNet: Category-Level 6D Object Pose and Size Estimation Using Dual Pose Network With Refined Learning of Pose Consistency

Multiple Instance Active Learning for Object Detection

AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning

Renovating Parsing R-CNN for Accurate Multiple Human Parsing

Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network

Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images

DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior

Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model

BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models

MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections

Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images

Few-Shot Learning With Visual Distribution Calibration and Cross-Modal Distribution Alignment

Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution

MagicEraser: Erasing Any Objects via Semantics-Aware Control

TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields

Semantics-aware Motion Retargeting with Vision-Language Models

CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval

Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the Wild

HiVLP: Hierarchical Interactive Video-Language Pre-Training

PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval

Co-Speech Gesture Synthesis by Reinforcement Learning With Contrastive Pre-Trained Rewards

papers (25)

CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation

Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE

VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction

Instance Segmentation in 3D Scenes Using Semantic Superpoint Tree Networks

DualPoseNet: Category-Level 6D Object Pose and Size Estimation Using Dual Pose Network With Refined Learning of Pose Consistency

Multiple Instance Active Learning for Object Detection

AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning

Renovating Parsing R-CNN for Accurate Multiple Human Parsing

Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network

Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images

DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior

Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model

BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models

MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections

Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images

Few-Shot Learning With Visual Distribution Calibration and Cross-Modal Distribution Alignment

Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution

MagicEraser: Erasing Any Objects via Semantics-Aware Control

TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields

Semantics-aware Motion Retargeting with Vision-Language Models

CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval

Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the Wild

HiVLP: Hierarchical Interactive Video-Language Pre-Training

PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval

Co-Speech Gesture Synthesis by Reinforcement Learning With Contrastive Pre-Trained Rewards