Daisuke Iso
Profile
Daisuke is a senior research scientist at Sony AI. He has been working on imaging and sensing technology for more than 10 years in both academia and industry. His research interests are computational photography, computer vision and machine learning. He received the B.E, M.E, and Ph.D. degrees in information and computer science from Keio University, Tokyo, Japan, in 2001, 2003, and 2006, respectively. He was a visiting scholar at Columbia University from 2011 to 2013.
Publications
Learning Hierarchical Line Buffer for Image Processing
ICCV, 2025 | Jiacheng Li, Feiran Li, Daisuke Iso
In recent years, neural networks have achieved significant progress in offline image processing. However, in online scenarios, particularly in on-chip implementations, memory usage emerges as a critical bottleneck due to the limited memory resources of integrated image proce...
Beyond RGB: Adaptive Parallel Processing for RAW Object Detection
ICCV, 2025 | Shani Gamrian, Hila Barel, Feiran Li, Masakazu Yoshimura*, Daisuke Iso
Object detection models are typically applied to standard RGB images processed through Image Signal Processing (ISP) pipelines, which are designed to enhance sensor-captured RAW images for human vision. However, these ISP functions can lead to a loss of critical information ...
Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution
ICCV, 2025 | Vlad Hosu, Lorenzo Agnolucci, Daisuke Iso, Dietmar Saupe*
Image Quality Assessment (IQA) measures and predicts perceived image quality by human observers. Although recent studies have highlighted the critical influence that variations in the scale of an image have on its perceived quality, this relationship has not been systematica...
ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge
CVPR, 2025 | Radu Berdan, Beril Besbinar, Christoph Reinders, Junji Otsuka*, Daisuke Iso
Edge-based computer vision models running on compact, resource-limited devices benefit greatly from using unprocessed, detail-rich RAW sensor data instead of processed RGB images. Training these models, however, necessitates large labeled RAW datasets, which are costly and o...
Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising
CVPR, 2025 | Feiran Li, Haiyang Jiang, Daisuke Iso
Noise synthesis is a promising solution for addressing the data shortage problem in data-driven low-light RAW image denoising. However, accurate noise synthesis methods often necessitate labor-intensive calibration and profiling procedures during preparation, preventing them...
UHD-IQA Benchmark Database: Pushing the Boundaries of Blind Photo Quality Assessment
ECCV, 2025 | Vlad Hosu, Lorenzo Agnolucci, Oliver Wiedemann, Daisuke Iso, Dietmar Saupe*
We introduce a novel Image Quality Assessment (IQA) dataset comprising 6073 UHD-1 (4K) images, annotated at a fixed width of 3840 pixels. Contrary to existing No-Reference (NR) IQA datasets, ours focuses on highly aesthetic photos of high technical quality, filling a gap in ...
RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation
WACV, 2025 | Christoph Reinders, Radu Berdan, Beril Besbinar, Junji Otsuka*, Daisuke Iso
Current deep learning approaches in computer vision primarily focus on RGB data sacrificing information. In contrast, RAW images offer richer representation, which is crucial for precise recognition, particularly in challenging conditions like low-light environments. The res...
MocoSFL: enabling cross-client collaborative self-supervised learning
ICLR, 2023 | Jingtao Li, Lingjuan Lyu, Daisuke Iso, Chaitali Chakrabarti*, Michael Spranger
Existing collaborative self-supervised learning (SSL) schemes are not suitable for cross-client applications because of their expensive computation and large local data requirements. To address these issues, we propose MocoSFL, a collaborative SSL framework based on Split Fe...