Lizhuang Ma

57

Papers

531

Total Citations

Papers (57)

Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection

PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection

COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction

MV-Adapter: Multi-View Consistent Image Generation Made Easy

Test-Time Domain Generalization for Face Anti-Spoofing

DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input

Rethinking Generalizable Face Anti-spoofing via Hierarchical Prototype-guided Distribution Refinement in Hyperbolic Space

DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding

Continuous Piecewise-Affine Based Motion Model for Image Animation

SuperMat: Physically Consistent PBR Material Estimation at Interactive Rates

3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations

MOS: Modeling Object-Scene Associations in Generalized Category Discovery

Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions

Pinco: Position-induced Consistent Adapter for Diffusion Transformer in Foreground-conditioned Inpainting

Interacted Object Grounding in Spatio-Temporal Human-Object Interactions

SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation

Stylized-Face: A Million-level Stylized Face Dataset for Face Recognition

PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model

Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification

Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes

ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-High Resolution Segmentation

Rethinking Efficient Lane Detection via Curve Modeling

LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints

HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization

Instance-Aware Domain Generalization for Face Anti-Spoofing

Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling

PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation

Make-It-3D: High-fidelity 3D Creation from A Single Image with Diffusion Prior

Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption

Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection

LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment

Contrastive Pseudo Learning for Open-World DeepFake Attribution

Face Anti-Spoofing via Disentangled Representation Learning

Human Correspondence Consensus for 3D Object Semantic Understanding

Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation

Generative Domain Adaptation for Face Anti-Spoofing

Hierarchical Contrastive Inconsistency Learning for Deepfake Video Detection

One-for-More: Continual Diffusion Model for Anomaly Detection

Mutually Reinforcing Structure with Proposal Contrastive Consistency for Few-Shot Object Detection

ATA: Adaptive Transformation Agent for Text-Guided Subject-Position Variable Background Inpainting

Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction

Real-IAD D³: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection

SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuning

ID-Sculpt: ID-aware 3D Head Generation from Single In-the-wild Portrait Image

Rethinking Reverse Distillation for Multi-Modal Anomaly Detection

Domain-Hallucinated Updating for Multi-Domain Face Anti-spoofing

A Theory of Non-acyclic Generative Flow Networks

Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text

Re-thinking Data Availability Attacks Against Deep Neural Networks

BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation

Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection

KeypointNet: A Large-Scale 3D Keypoint Dataset Aggregated From Numerous Human Annotations

Contrastive Learning for Compact Single Image Dehazing