arXiv subjects

Dilshan Godaliyadda

Publications and source records attributed to Dilshan Godaliyadda.

5 recordsLinked to original sources

arXiv2026

MetaTele: Compact Refractive Metasurface Computational Telephoto Camera

Smartphone cameras face fundamental form-factor constraints that limit their optical magnification, primarily due to the difficulty of reducing a lens assembly's telephoto ratio, the ratio between total track length (TTL) and effective focal length (EFL). Currently, conventional refractive optics struggle to achieve a telephoto ratio below 0.5 without requiring multiple bulky elements to correct optical aberrations. In this paper, we introduce MetaTele, a novel optics-algorithm co-design that breaks this bottleneck. MetaTele explicitly decouples the acquisition of scene structure and color information. First, it utilizes a compact refractive-metasurface optical assembly to capture a fine-detail structure image under a narrow wavelength band, inherently avoiding severe chromatic aberrations. Second, it captures a broadband color cue using the same optics; although this cue is heavily corrupted by chromatic aberrations, it retains sufficient spectral information to guide post-processing. We then employ a custom one-step diffusion model to computationally fuse these two raw measurements, successfully colorizing the structure image while correcting for system aberrations. We demonstrate a MetaTele prototype, achieving an unprecedented telephoto ratio of 0.44 with a TTL of just 13 mm for RGB imaging, paving the way for DSLR-level telephoto capabilities within smartphone form factors.

eess.IV↗

arXiv2026

Direct Kernel Optimization: Efficient Design for Opto-Electronic Convolutional Neural Networks

Hybrid opto-electronic neural networks combine optical front-ends with electronic back-ends to perform vision tasks, but joint end-to-end (E2E) optimization of optical and electronic components is computationally expensive due to large parameter spaces and repeated optical convolutions. We propose Direct Kernel Optimization (DKO), a two-stage training framework that first trains a conventional electronic CNN and then synthesizes optical kernels to replicate the first-layer convolutional filters, reducing optimization dimensionality and avoiding hefty simulated optical convolutions during optimization. We evaluate DKO in simulation on a monocular depth estimation model and show that it achieves twice the accuracy of E2E training under equal computational budgets while reducing training time. Given the substantial computational challenges of optimizing hybrid opto-electronic systems, our results position DKO as a scalable optimization approach to train and realize these systems.

eess.IV↗

arXiv2025

F2IDiff: Real-world Image Super-resolution using Feature to Image Diffusion Foundation Model

With the advent of Generative AI, Single Image Super-Resolution (SISR) quality has seen substantial improvement, as the strong priors learned by Text-2-Image Diffusion (T2IDiff) Foundation Models (FM) can bridge the gap between High-Resolution (HR) and Low-Resolution (LR) images. However, flagship smartphone cameras have been slow to adopt generative models because strong generation can lead to undesirable hallucinations. For substantially degraded LR images, as seen in academia, strong generation is required and hallucinations are more tolerable because of the wide gap between LR and HR images. In contrast, in consumer photography, the LR image has substantially higher fidelity, requiring only minimal hallucination-free generation. We hypothesize that generation in SISR is controlled by the stringency and richness of the FM's conditioning feature. First, text features are high level features, which often cannot describe subtle textures in an image. Additionally, Smartphone LR images are at least $12MP$, whereas SISR networks built on T2IDiff FM are designed to perform inference on much smaller images ($<1MP$). As a result, SISR inference has to be performed on small patches, which often cannot be accurately described by text feature. To address these shortcomings, we introduce an SISR network built on a FM with lower-level feature conditioning, specifically DINOv2 features, which we call a Feature-to-Image Diffusion (F2IDiff) Foundation Model (FM). Lower level features provide stricter conditioning while being rich descriptors of even small patches.

cs.CV↗

arXiv2025

Personalized Generative Low-light Image Denoising and Enhancement

Modern cameras' performance in low-light conditions remains suboptimal due to fundamental limitations in photon shot noise and sensor read noise. Generative image restoration methods have shown promising results compared to traditional approaches, but they suffer from hallucinatory content generation when the signal-to-noise ratio (SNR) is low. Leveraging the availability of personalized photo galleries of the users, we introduce Diffusion-based Personalized Generative Denoising (DiffPGD), a new approach that builds a customized diffusion model for individual users. Our key innovation lies in the development of an identity-consistent physical buffer that extracts the physical attributes of the person from the gallery. This ID-consistent physical buffer serves as a robust prior that can be seamlessly integrated into the diffusion model to restore degraded images without the need for fine-tuning. Over a wide range of low-light testing scenarios, we show that DiffPGD achieves superior image denoising and enhancement performance compared to existing diffusion-based denoising approaches. Our project page can be found at \href{https://genai-restore.github.io/DiffPGD/}{\textcolor{purple}{\textbf{https://genai-restore.github.io/DiffPGD/}}}.

cs.CV↗

arXiv2025

Shared Neural Space: Unified Precomputed Feature Encoding for Multi-Task and Cross Domain Vision

The majority of AI models in imaging and vision are customized to perform on specific high-precision task. However, this strategy is inefficient for applications with a series of modular tasks, since each requires a mapping into a disparate latent domain. To address this inefficiency, we proposed a universal Neural Space (NS), where an encoder-decoder framework pre-computes features across vision and imaging tasks. Our encoder learns transformation aware, generalizable representations, which enable multiple downstream AI modules to share the same feature space. This architecture reduces redundancy, improves generalization across domain shift, and establishes a foundation for effecient multi-task vision pipelines. Furthermore, as opposed to larger transformer backbones, our backbone is lightweight and CNN-based, allowing for wider across hardware. We furthur demonstrate that imaging and vision modules, such as demosaicing, denoising, depth estimation and semantic segmentation can be performed efficiently in the NS.

cs.CV↗