ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Xiaoyu Shi

Xiaoyu Shi

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 5:45 AM AMS

11

papers

986

total citations

papers (11)

FlowFormer: A Transformer Architecture for Optical Flow

FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting

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

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

A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

A Unified Conditional Framework for Diffusion-based Image Restoration

NEURIPS 2023arXiv

Context-PIPs: Persistent Independent Particles Demands Spatial Context Features

NEURIPS 2023arXiv

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

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

FlexDrive: Toward Trajectory Flexibility in Driving Scene Gaussian Splatting Reconstruction and Rendering