Despite the absence of high-resolution ground truth features, we find that training JAFAR at low upsampling ratios and resolutions generalizes remarkably well to significantly higher output scales (4/n)

🚀Thrilled to introduce JAFAR—a lightweight, flexible, plug-and-play module that upsamples features from any Foundation Vision Encoder to any desired output resolution (1/n)

Paper : arxiv.org/abs/2506.11136
Project Page: jafar-upsampler.github.io
Github: github.com/PaulCouairon...