Chao Xu

64

Papers

273

Total Citations

Papers (64)

CNNpack: Packing Convolutional Neural Networks in the Frequency Domain

MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos

FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio

Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction

DiC: Rethinking Conv3x3 Designs in Diffusion Models

Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition

EvDiG: Event-guided Direct and Global Components Separation

Polarization Guided Mask-Free Shadow Removal

Image Processing GNN: Breaking Rigidity in Super-Resolution

NB-GTR: Narrow-Band Guided Turbulence Removal

One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion

RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control

SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models

Parametric T-Spline Face Morphable Model for Detailed Fitting in Shape Subspace

Environment Upgrade Reinforcement Learning for Non-Differentiable Multi-Stage Pipelines

Revisiting Perspective Information for Efficient Crowd Counting

Frequency Domain Compact 3D Convolutional Neural Networks

Neuromorphic Camera Guided High Dynamic Range Imaging

A Semi-Supervised Assessor of Neural Architectures

CARS: Continuous Evolution for Efficient Neural Architecture Search

AdderNet: Do We Really Need Multiplications in Deep Learning?

On Positive-Unlabeled Classification in GAN

Learning Student Networks in the Wild

Pre-Trained Image Processing Transformer

HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation

HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

Manifold Regularized Dynamic Network Pruning

Hire-MLP: Vision MLP via Hierarchical Rearrangement

Source-Free Domain Adaptation via Distribution Estimation

Region-Aware Face Swapping

An Image Patch Is a Wave: Phase-Aware Vision MLP

Patch Slimming for Efficient Vision Transformers

GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts

Network Expansion for Practical Training Acceleration

Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution

High-Fidelity Generalized Emotional Talking Face Generation With Multi-Modal Emotion Space Learning

1000 FPS HDR Video With a Spike-RGB Hybrid Camera

Data-Free Learning of Student Networks

EvIntSR-Net: Event Guided Multiple Latent Frames Reconstruction and Super-Resolution

DTVNet: Dynamic Time-lapse Video Generation via Single Still Image

D&D: Learning Human Dynamics from Dynamic Camera

Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping

Neural Underwater Scene Representation

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations

Label Shift Meets Online Learning: Ensuring Consistent Adaptation with Universal Dynamic Regret

Event-based Visual Vibrometry

BokehDiff: Neural Lens Blur with One-Step Diffusion

PlaNet: Learning to Mitigate Atmospheric Turbulence in Planetary Images

AeroGTO: An Efficient Graph-Transformer Operator for Learning Large-Scale Aerodynamics of 3D Vehicle Geometries

Learning Versatile Filters for Efficient Convolutional Neural Networks

Learning from Bad Data via Generation

UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging

Searching for Low-Bit Weights in Quantized Neural Networks

SCOP: Scientific Control for Reliable Neural Network Pruning

Learning to dehaze with polarization

Augmented Shortcuts for Vision Transformers

Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model

GhostNetV2: Enhance Cheap Operation with Long-Range Attention

Linear tree shap

Towards Higher Ranks via Adversarial Weight Pruning

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization

Beyond Filters: Compact Feature Map for Portable Deep Model

LegoNet: Efficient Convolutional Neural Networks with Lego Filters