Picture for Hong Cai

Hong Cai

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer

Add code
Jul 16, 2024
Viaarxiv icon

ToSA: Token Selective Attention for Efficient Vision Transformers

Add code
Jun 13, 2024
Viaarxiv icon

SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations

Add code
Apr 11, 2024
Viaarxiv icon

OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation

Add code
Mar 26, 2024
Viaarxiv icon

FutureDepth: Learning to Predict the Future Improves Video Depth Estimation

Add code
Mar 19, 2024
Viaarxiv icon

DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions

Add code
Mar 18, 2024
Viaarxiv icon

Neural Mesh Fusion: Unsupervised 3D Planar Surface Understanding

Add code
Feb 26, 2024
Viaarxiv icon

HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation

Add code
Jan 15, 2024
Viaarxiv icon

Efficient option pricing with unary-based photonic computing chip and generative adversarial learning

Add code
Aug 08, 2023
Viaarxiv icon

MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation

Add code
Jul 26, 2023
Viaarxiv icon