ๆœบๅ™จไน‹ๅฟƒ JIQIZHIXIN (@jiqizhixin)

2026-01-25 | โค๏ธ 298 | ๐Ÿ” 43


What if we could model vision like a wave moving through space?

Researchers from Peking & Tsinghua Universities present WaveFormer.

They treat image features as signals governed by a wave equation, explicitly controlling how low-to-high frequency details evolve across network layers.

This new Wave Propagation Operator outperforms standard Vision Transformers in image classification, detection, and segmentation, achieving up to 1.6x higher throughput with 30% fewer computations.

WaveFormer: Frequency-Time Decoupled Vision Modeling with Wave Equation

Paper: https://t.co/8hxGVhuXUv Code: https://t.co/5ccfQ31yDS

Our report: https://t.co/SsKI5vM1ZL

๐Ÿ“ฌ PapersAccepted by Jiqizhixin

๋ฏธ๋””์–ด

image


Tags

3D-Vision generation