Ran Yi

35

Papers

146

Total Citations

Papers (35)

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

SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis

Rectified Diffusion Guidance for Conditional Generation

Continuous Piecewise-Affine Based Motion Model for Image Animation

SuperMat: Physically Consistent PBR Material Estimation at Interactive Rates

Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner

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

MOS: Modeling Object-Scene Associations in Generalized Category Discovery

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

Weighted Poisson-disk Resampling on Large-Scale Point Clouds

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

AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model

Re-thinking Data Availability Attacks Against Deep Neural Networks

Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction

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

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

SMaRt: Improving GANs with Score Matching Regularity

Content-Sensitive Supervoxels via Uniform Tessellations on Video Manifolds

APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs

Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping

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

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

Instance-Aware Domain Generalization for Face Anti-Spoofing

Multimodal Industrial Anomaly Detection via Hybrid Fusion

Towards Artistic Image Aesthetics Assessment: A Large-Scale Dataset and a New Method

Fast Computation of Content-Sensitive Superpixels and Supervoxels Using Q-Distances

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

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

Generative Domain Adaptation for Face Anti-Spoofing

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

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