Zhaoyang Huang

14

Papers

62

Total Citations

Papers (14)

Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow

ZoLA: Zero-Shot Creative Long Animation Generation with Short Video Model

BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events

VS-Net: Voting With Segmentation for Visual Localization

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation

PATS: Patch Area Transportation With Subdivision for Local Feature Matching

Prior Guided Dropout for Robust Visual Localization in Dynamic Environments

VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation

FlowFormer: A Transformer Architecture for Optical Flow

GS-DiT: Advancing Video Generation with Dynamic 3D Gaussian Fields through Efficient Dense 3D Point Tracking

BlinkTrack: Feature Tracking over 80 FPS via Events and Images

DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation

Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields

Context-PIPs: Persistent Independent Particles Demands Spatial Context Features