Yuanhao Cai

PhD student@Johns Hopkins University·美国·OpenReview

研究方向

3D Reconstruction · Snapshot Compressive Imaging · Hyperspectral Image Reconstruction · Medical Image Enhancement · Image Restoration · Deep Learning · Human Pose Estimation

5.6

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning

ICLR 2026Oral

3.5

Flow-Matching Guided Deep Unfolding for Hyperspectral Image Reconstruction

ICLR 2026Rejected

二作

7.8

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions

合作者 (20)

Yuanhao Cai

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning

Flow-Matching Guided Deep Unfolding for Hyperspectral Image Reconstruction

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS

Are Pixel-Wise Metrics Reliable for Computerized Tomography Reconstruction?

LucidFusion: Generating 3D Gaussians with Arbitrary Unposed Images