JAFAR: Jack up Any Feature at Any Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Couairon, Paul, Chambon, Loick, Serrano, Louis, Haugeard, Jean-Emmanuel, Cord, Matthieu, Thome, Nicolas
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917228011585536
author Couairon, Paul
Chambon, Loick
Serrano, Louis
Haugeard, Jean-Emmanuel
Cord, Matthieu
Thome, Nicolas
author_facet Couairon, Paul
Chambon, Loick
Serrano, Louis
Haugeard, Jean-Emmanuel
Cord, Matthieu
Thome, Nicolas
contents Foundation Vision Encoders have become essential for a wide range of dense vision tasks. However, their low-resolution spatial feature outputs necessitate feature upsampling to produce the high-resolution modalities required for downstream tasks. In this work, we introduce JAFAR, a lightweight and flexible feature upsampler that enhances the spatial resolution of visual features from any Foundation Vision Encoder to an arbitrary target resolution. JAFAR employs an attention-based module designed to promote semantic alignment between high-resolution queries, derived from low-level image features, and semantically enriched low-resolution keys, using Spatial Feature Transform (SFT) modulation. Notably, despite the absence of high-resolution supervision, we demonstrate that learning at low upsampling ratios and resolutions generalizes remarkably well to significantly higher output scales. Extensive experiments show that JAFAR effectively recovers fine-grained spatial details and consistently outperforms existing feature upsampling methods across a diverse set of downstream tasks. Project page at https://jafar-upsampler.github.io
format Preprint
id arxiv_https___arxiv_org_abs_2506_11136
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle JAFAR: Jack up Any Feature at Any Resolution
Couairon, Paul
Chambon, Loick
Serrano, Louis
Haugeard, Jean-Emmanuel
Cord, Matthieu
Thome, Nicolas
Computer Vision and Pattern Recognition
Image and Video Processing
Foundation Vision Encoders have become essential for a wide range of dense vision tasks. However, their low-resolution spatial feature outputs necessitate feature upsampling to produce the high-resolution modalities required for downstream tasks. In this work, we introduce JAFAR, a lightweight and flexible feature upsampler that enhances the spatial resolution of visual features from any Foundation Vision Encoder to an arbitrary target resolution. JAFAR employs an attention-based module designed to promote semantic alignment between high-resolution queries, derived from low-level image features, and semantically enriched low-resolution keys, using Spatial Feature Transform (SFT) modulation. Notably, despite the absence of high-resolution supervision, we demonstrate that learning at low upsampling ratios and resolutions generalizes remarkably well to significantly higher output scales. Extensive experiments show that JAFAR effectively recovers fine-grained spatial details and consistently outperforms existing feature upsampling methods across a diverse set of downstream tasks. Project page at https://jafar-upsampler.github.io
title JAFAR: Jack up Any Feature at Any Resolution
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2506.11136