and Prof. Changick Kim (corresponding author)>
A research team led by Professor Changick Kim from EE, through joint research with researchers from MIT and Microsoft, has developed ‘Upsample Anything’—a universal technology that enhances AI vision performance even with limited GPU memory.
Submitted to CVPR 2026, the world’s most prestigious computer vision and AI conference, the paper achieved the extraordinary feat of ranking 1st overall among all 4,089 submissions.
Furthermore, in recognition of its highly efficient utilization of computational resources, the technology was awarded the ‘CVPR Compute Gold Star’—an elite distinction presented to only 18 of the submitted papers. The team was also named a ‘Transparency Champion’ for its outstanding contributions to research transparency and reproducibility.
This sweeping success widely recognizes the core elements of responsible AI research, encompassing not only raw performance but also computational efficiency, open-source code disclosure, and experimental reproducibility.
Recently, humanoid robots, autonomous driving systems, and AI based on world models (AI models that learn and predict the physical environment and changes of the real world) have been compressing input images into low-resolution features (core information extracted from images by AI) to increase computational speed and reduce memory usage.
However, during the compression process, a problem occurs where important visual information, such as small objects, thin structures, and minute defects, is lost. Conversely, processing all images at high resolution from the beginning requires massive GPU memory and computational resources, making real-time processing difficult. This has remained an unresolved challenge for a long time in situations where small devices like smartphones or robots, where mobility is crucial, must precisely perceive their surrounding environment.
To overcome these limitations, the research team developed a training-free (requiring no additional data training) upsampling technology that restores low-resolution feature information into high resolution by utilizing the edge and structural information of the input image.
Existing technologies required a separate retraining or complex optimization process to be applied to new environments or data. In contrast, ‘Upsample Anything’ developed by the research team can find the optimal restoration method using just a single input image, allowing it to be immediately applied to various environments.
In addition, by compressing and utilizing only core information instead of storing and processing all visual information at high resolution, GPU memory usage was significantly reduced. Based on a 224×224 size image (approximately 50,000 pixels) widely used in AI research, the research team restored visual information close to the original with a short calculation of about 0.4 seconds, achieving a performance that improves GPU memory efficiency by up to 16 times.
This means that artificial intelligence can perceive its surrounding environment more precisely even with limited computational resources. Therefore, this technology is expected to be widely used in various next-generation artificial intelligence fields, such as small devices like smartphones, as well as humanoid robots that need to accurately identify and manipulate small objects, autonomous driving systems, and on-device AI.
Professor Changick Kim said, “This technology is an algorithm that can significantly increase the visual precision of artificial intelligence with fewer resources, and it is expected to accelerate the commercialization of humanoid robots and on-device AI.” He added, “It is even more meaningful because it was recognized at CVPR not only for its performance but also for its computational efficiency and research transparency.”
This research was participated in by KAIST PhD student Minseok Seo as the first author, and this achievement was presented on June 7 at ‘CVPR 2026,’ the world’s most prestigious conference in the field of artificial intelligence and computer vision.
- Paper Title: Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling
- DOI:10.48550/arXiv.2511.16301
- Author Information: Minseok Seo (First Author), Mark Hamilton (MIT, Microsoft, Second Author), Changick Kim (Corresponding Author)
