Yifan Liu

29

Papers

191

Total Citations

Papers (29)

Efficient Semantic Video Segmentation with Per-frame Inference

Representative Graph Neural Network

MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models

Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions

GaussianReg: Rapid 2D/3D Registration for Emergency Surgery via Explicit 3D Modeling with Gaussian Primitives

U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation

High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field

Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion

Inter-X: Towards Versatile Human-Human Interaction Analysis

MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection

Structured Knowledge Distillation for Semantic Segmentation

Generic Perceptual Loss for Modeling Structured Output Dependencies

ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation

Channel-Wise Knowledge Distillation for Dense Prediction

A Simple Baseline for Semi-Supervised Semantic Segmentation With Strong Data Augmentation

3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection

FedPD: Federated Open Set Recognition with Parameter Disentanglement

CTVIS: Consistent Training for Online Video Instance Segmentation

Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation

SegPrompt: Boosting Open-World Segmentation via Category-Level Prompt Learning

Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving

Instance-Aware Embedding for Point Cloud Instance Segmentation

Controllable Shadow Generation Using Pixel Height Maps

Semantic-Guided Multi-Mask Image Harmonization

Enforcing Geometric Constraints of Virtual Normal for Depth Prediction

InfoBridge: Balanced Multimodal Integration through Conditional Dependency Modeling

Learning Efficient and Generalizable Human Representation with Human Gaussian Model

Anti-Tamper Protection for Unauthorized Individual Image Generation

Back-Modality: Leveraging Modal Transformation for Data Augmentation