Image Processing Techniques and Applications

Derniers papiers

• ZoomDiff: A High-Fidelity Diffusion Model for Dual-Camera Smooth Zooming

  Jiayi Zhang, Renlong Wu, Yukang Ding, Sibin Deng, Wangmeng Zuo · 24 septembre 2026

  Digital zoom transitions between dual cameras often exhibit conspicuous discontinuities in geometric structure and chromatic consistency, degrading the user experience. While recent dual-camera smooth zoom (DCSZ) methods attempt to mitigate this by fine-tuning frame interpolation (FI) models on DCSZ…

• LensStyle: Learning the Optical Aesthetics for Controllable Stylized Lens Effect Rendering

  Yachuan Huang, Liwen Xiao, Liao Shen, Qiwen Wang, Huiqiang Sun, Zhiyu Pan, Zhiguo Cao · 7 septembre 2026

  The visual aesthetics of photographs are deeply influenced by lens characteristics such as aperture shape, optical vignetting and optical diffraction, which together define a camera's unique optical style. Existing lens effect rendering methods primarily focus on accurately simulating the blur trans…

• Learning to Zoom Efficiently with a Contrastive Curriculum

  Falko Helm, Iryna Gurevych · 4 septembre 2026

  Using a zoom-in tool is an important foundational part of modern visual agents, because it allows to efficiently handle tasks involving high-resolution images. Most previous methods need an extensive warm-start supervised fine-tuning phase for teaching models zoom-in. We show that this is not necess…

• The RealDefocus Benchmark for Defocus Deblurring

  Tim Seizinger, Zhuyun Zhou, Radu Timofte · 24 juillet 2026

  Single-Image Defocus Deblurring (SIDD) aims to recover an all-in-focus image from a single defocused observation, but rigorous and reproducible evaluation remains challenging due to the scarcity of realistic, high-resolution datasets with well-aligned defocused/sharp pairs and standardized protocols…

• Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing

  Rishubh Parihar, Or Patashnik, Daniil Ostashev, R. Venkatesh Babu, Daniel Cohen-Or, Kuan-Chieh Wang · 22 juillet 2026

  Instruction-based image editing offers a powerful and intuitive way to manipulate images through natural language. Yet, relying solely on text instructions limits fine-grained control over the extent of edits. We introduce Kontinuous Kontext, an instruction-driven editing model that provides a new d…

• Video to All-in-focus Image Reconstruction Algorithm for Automated Microscopic Urinalysis

  Chinmay Nema, Hari Om Aggrawal, Dipam Goswami, Rajiv Gupta, Vinti Agarwal · 16 juillet 2026

  Microscopic urinalysis is a routine diagnostic test at hospitals. Recent studies have demonstrated the effectiveness of deep learning methods to automate microscopic urinalysis. These methods rely on high-quality images of the urine samples in which each cell is clearly identifiable. However, in pra…

• Practical High-Fidelity Novel-View Synthesis of Mounted Lepidoptera

  Kristof Overdulve, Lode Jorissen, Nick Michiels · 1 juillet 2026

  Mounted butterflies are among the most striking objects in natural history collections. However, their beauty is notoriously hard to digitize in 3D: they are small and fragile, with microscopic hairs and vein structures. Capturing them in sufficient detail, therefore, requires a macro lens, which ha…

• Unsupervised Learning Based Focal Stack Camera Depth Estimation

  Zhengyu Huang, Weizhi Du, Theodore B. Norris · 8 juin 2026

  We propose an unsupervised deep learning based method to estimate depth from focal stack camera images. On the NYU-v2 dataset, our method achieves much better depth estimation accuracy compared to single-image based methods.…

• Neural Low-Discrepancy Sequences

  Michael Etienne Van Huffel, Nathan Kirk, Makram Chahine, Daniela Rus, T. Konstantin Rusch · 2 juin 2026

  Low-discrepancy points are designed to efficiently fill the space in a uniform manner. This uniformity is highly advantageous in many problems in science and engineering, including in numerical integration, computer vision, machine perception, computer graphics, machine learning, and simulation. Whe…

• Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering

  Gerasimos Chatzoudis, Zhuowei Li, Gemma E. Moran, Hao Wang, Dimitris N. Metaxas · 28 mai 2026

  Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. We study whether sparse visual features can be used not only for post-hoc analysis, but also to steer frozen vision-langu…

• DefocusTrackerAI -- A Generalized Framework for the Automatic Detection of Defocused Particle Images

  Gonçalo Coutinho, Ana S. Moita, António L. N. Moreira, Massimiliano Rossi · 25 mai 2026

  The present work introduces DefocusTrackerAI, a generalized deep-learning framework for the automatic detection and position estimation of defocused particle images from any kind of optical configuration without compromising uncertainty and recall, intended as a follow-up of the open-source project …

• HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling

  Xianjie Liu, Yiman Hu, Yixiong Zou, Liang Wu, Jian Xu, Bo Zheng · 20 mai 2026

  Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tasks. However, their performance on high-resolution images remains suboptimal. While existing approaches often attribute this limitation to perceptual constraints and argue that MLLMs struggle to recogniz…

• DIPLI: Deep Image Prior Lucky Imaging for Blind Astronomical Image Restoration

  Suraj Singh, Anastasia Batsheva, Oleg Y. Rogov, Ahmed Bouridane · 6 mai 2026

  Modern image restoration and super-resolution methods utilize deep learning due to its superior performance compared to traditional algorithms. However, deep learning typically requires large labeled training datasets, which are rarely available in astrophotography. Deep Image Prior (DIP) bypasses t…

• Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization

  R\'ois\'in Luo, Alexandru Drimbarean, James McDermott, Colm O'Riordan · 29 avril 2026

  This paper explores a novel paradigm in low-bit (i.e. 4-bits or lower) quantization, differing from existing state-of-the-art methods, by framing optimal quantization as an architecture search problem within convolutional neural networks (ConvNets). Our framework, dubbed \textbf{CoRa} (Optimal Quant…

• MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design

  Zhen Zheng, Xiaonan Song, Chuanjie Liu · 23 avril 2026

  Quantization has become one of the most effective methodologies to compress LLMs into smaller size. However, the existing quantization solutions still show limitations of either non-negligible accuracy drop or low system efficiency. In this paper, we propose MixLLM that explores the optimization spa…

• Visual Sparse Steering (VS2): Unsupervised Adaptation for Image Classification using Sparsity-Guided Steering Vectors

  Gerasimos Chatzoudis, Zhuowei Li, Gemma E. Moran, Hao Wang, Dimitris N. Metaxas · 16 avril 2026

  Steering vision foundation models at test time, without updating foundation-model weights or using labeled target data, is a desirable yet challenging goal. We present Visual Sparse Steering (VS2), a lightweight, label-free adaptation method that constructs a steering vector from sparse features ext…

• Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

  Bryan Sangwoo Kim, Jeongsol Kim, Jong Chul Ye · 13 avril 2026

  Modern single-image super-resolution (SISR) models deliver photo-realistic results at the scale factors on which they are trained, but collapse when asked to magnify far beyond that regime. We address this scalability bottleneck with Chain-of-Zoom (CoZ), a model-agnostic framework that factorizes SI…

• Towards Minimal Focal Stack in Shape from Focus

  Khurram Ashfaq, Muhammad Tariq Mahmood · 3 avril 2026

  Shape from Focus (SFF) is a depth reconstruction technique that estimates scene structure from focus variations observed across a focal stack, that is, a sequence of images captured at different focus settings. A key limitation of SFF methods is their reliance on densely sampled, large focal stacks,…

• Zero-Shot Depth from Defocus

  Yiming Zuo, Hongyu Wen, Venkat Subramanian, Patrick Chen, Karhan Kayan, Mario Bijelic, Felix Heide, Jia Deng · 30 mars 2026

  Depth from Defocus (DfD) is the task of estimating a dense metric depth map from a focus stack. Unlike previous works overfitting to a certain dataset, this paper focuses on the challenging and practical setting of zero-shot generalization. We first propose a new real-world DfD benchmark ZEDD, which…

• SpiderCam: Low-Power Snapshot Depth from Differential Defocus

  Marcos A. Ferreira, Tianao Li, John Mamish, Josiah Hester, Yaman Sangar, Qi Guo, Emma Alexander · 19 mars 2026

  We introduce SpiderCam, an FPGA-based snapshot depth-from-defocus camera which produces 480x400 sparse depth maps in real-time at 32.5 FPS over a working range of 52 cm while consuming 624 mW of power in total. SpiderCam comprises a custom camera that simultaneously captures two differently focused …

• QKV Projections Require a Fraction of Their Memory

  Malik Khalaf, Yara Shamshoum, Nitzan Hodos, Yuval Sieradzki, Assaf Schuster · 3 mars 2026

  The Multi-Head Attention mechanism is central to LLM operation, and multiple works target its compute and memory efficiency during training. While most works focus on approximating the scaled dot product, the memory consumption of the linear projections that compute the $Q$, $K$, and $V$ tensors fro…

• Exploiting Low-Dimensional Manifold of Features for Few-Shot Whole Slide Image Classification

  Conghao Xiong, Zhengrui Guo, Zhe Xu, Yifei Zhang, Raymond Kai-Yu Tong, Si Yong Yeo, Hao Chen, Joseph J. Y. Sung, Irwin King · 3 mars 2026

  Few-shot Whole Slide Image (WSI) classification is severely hampered by overfitting. We argue that this is not merely a data-scarcity issue but a fundamentally geometric problem. Grounded in the manifold hypothesis, our analysis shows that features from pathology foundation models exhibit a low-dime…

• Depth from Defocus via Direct Optimization

  Holly Jackson, Caleb Adams, Ignacio Lopez-Francos, Benjamin Recht · 20 février 2026

  Though there exists a reasonable forward model for blur based on optical physics, recovering depth from a collection of defocused images remains a computationally challenging optimization problem. In this paper, we show that with contemporary optimization methods and reasonable computing resources, …

• Breaking the Sub-Millimeter Barrier: Eyeframe Acquisition from Color Images

  Manel Guzmán, Antonio Agudo · 19 février 2026

  Eyeframe lens tracing is an important process in the optical industry that requires sub-millimeter precision to ensure proper lens fitting and optimal vision correction. Traditional frame tracers rely on mechanical tools that need precise positioning and calibration, which are time-consuming and req…

• EasyControlEdge: A Foundation-Model Fine-Tuning for Edge Detection

  Hiroki Nakamura, Hiroto Iino, Masashi Okada, Tadahiro Taniguchi · 19 février 2026

  We propose EasyControlEdge, adapting an image-generation foundation model to edge detection. In real-world edge detection (e.g., floor-plan walls, satellite roads/buildings, and medical organ boundaries), crispness and data efficiency are crucial, yet producing crisp raw edge maps with limited train…