Shengfeng He

58

Papers

174

Total Citations

Papers (58)

OneRestore: A Universal Restoration Framework for Composite Degradation

Delving into Multimodal Prompting for Fine-Grained Visual Classification

Rethinking Multi-view Representation Learning via Distilled Disentangling

NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting

RePOSE: 3D Human Pose Estimation via Spatio-Temporal Depth Relational Consistency

Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency

Cross-Subject Mind Decoding from Inaccurate Representations

Stable Score Distillation

Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation

OmniVTON: Training-Free Universal Virtual Try-On

Adversarial Attacks on Event-Based Pedestrian Detectors: A Physical Approach

D3still: Decoupled Differential Distillation for Asymmetric Image Retrieval

Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation

Beyond Textual Constraints: Learning Novel Diffusion Conditions with Fewer Examples

Instruct2See: Learning to Remove Any Obstructions Across Distributions

Real-Time Salient Object Detection With a Minimum Spanning Tree

Exemplar-Driven Top-Down Saliency Detection via Deep Association

DeshadowNet: A Multi-Context Embedding Deep Network for Shadow Removal

Single Image Reflection Removal Beyond Linearity

Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics

Context-Aware Spatio-Recurrent Curvilinear Structure Segmentation

Context-Aware and Scale-Insensitive Temporal Repetition Counting

Don't Hit Me! Glass Detection in Real-World Scenes

Reciprocal Transformations for Unsupervised Video Object Segmentation

Delving Deep Into Many-to-Many Attention for Few-Shot Video Object Segmentation

Learning From the Master: Distilling Cross-Modal Advanced Knowledge for Lip Reading

Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-View Transformation

Discovering Interpretable Latent Space Directions of GANs Beyond Binary Attributes

Spatially-Invariant Style-Codes Controlled Makeup Transfer

High-Resolution Face Swapping via Latent Semantics Disentanglement

Faithful Extreme Rescaling via Generative Prior Reciprocated Invertible Representations

Co-Advise: Cross Inductive Bias Distillation

A Simple Data Mixing Prior for Improving Self-Supervised Learning

Shunted Self-Attention via Multi-Scale Token Aggregation

Curricular Contrastive Regularization for Physics-Aware Single Image Dehazing

Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval

Oriented Object Proposals

Delving Into Salient Object Subitizing and Detection

Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery

From Contexts to Locality: Ultra-High Resolution Image Segmentation via Locality-Aware Contextual Correlation

From Continuity to Editability: Inverting GANs With Consecutive Images

Deep Video Demoireing via Compact Invertible Dyadic Decomposition

CIRI: Curricular Inactivation for Residue-aware One-shot Video Inpainting

RIGID: Recurrent GAN Inversion and Editing of Real Face Videos

Diffuse3D: Wide-Angle 3D Photography via Bilateral Diffusion

TENet: Triple Excitation Network for Video Salient Object Detection

Editing Out-of-Domain GAN Inversion via Differential Activations

Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization

Knowledge Bridger: Towards Training-Free Missing Modality Completion

MODfinity: Unsupervised Domain Adaptation with Multimodal Information Flow Intertwining

Stroke2Sketch: Harnessing Stroke Attributes for Training-Free Sketch Generation

Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification

ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition

Instance-Level Video Depth in Groups Beyond Occlusions

Dr. Tongue: Sign-Oriented Multi-label Detection for Remote Tongue Diagnosis

Occlusion-Insensitive Talking Head Video Generation via Facelet Compensation

PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem Equilibrium

Active Matting