Ailing Zeng

29

Papers

463

Total Citations

Papers (29)

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation

GPAvatar: Generalizable and Precise Head Avatar from Image(s)

AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

IDOL: Instant Photorealistic 3D Human Creation from a Single Image

Open-World Human-Object Interaction Detection via Multi-modal Prompts

MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls

SkillMimic: Learning Basketball Interaction Skills from Demonstrations

FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions

From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels

HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation

Neural Interactive Keypoint Detection

DeciWatch: A Simple Baseline for 10× Efficient 2D and 3D Pose Estimation

SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos

HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling

Differentiable Kernel Evolution

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

HumanTOMATO: Text-aligned Whole-body Motion Generation

Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes

One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer

Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

Human Pose Regression With Residual Log-Likelihood Estimation

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction

DreamWaltz: Make a Scene with Complex 3D Animatable Avatars

SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

A Comprehensive Benchmark for Neural Human Radiance Fields