arXiv subjects

Debabrata Mandal

Publications and source records attributed to Debabrata Mandal.

8 recordsLinked to original sources

arXiv2026

DeltaCam: Differential Intrinsic Camera Modeling for Video Generation

Incorporating camera intrinsics into video generation models offers a principled way to control not only scene dynamics but also the imaging process that governs visual appearance. Prior work has primarily focused on extrinsic control, such as camera pose and motion, while treating intrinsic camera parameters as implicit or fixed. A key bottleneck is the lack of large-scale video datasets with accurate and diverse temporally varying camera metadata, which makes learning absolute camera parameterizations difficult. As a result, current models struggle to incorporate photographic camera behavior, including depth-of-field transitions, exposure variations, lens distortions, and color processing, in a controllable and temporally consistent manner. We introduce DeltaCam, a video diffusion framework that models camera behavior through $Δ$-parameterized neural camera adaptors, operating on relative changes in camera motion and intrinsics instead of absolute states. By learning this differential formulation from synthetic video data, we mitigate reliance on precise real-world camera labels and enable smooth, consistent control over imaging factors such as focal length, aperture, ISO, color temperature, and lens distortion. We extend this framework to real-world footage through two mechanisms: finetuning the controls on real image-metadata pairs for precise shot matching, and extracting disentangled embeddings for implicit video-to-video style transfer without requiring explicit camera parameters. By effectively separating scene content from intrinsic imaging behavior, DeltaCam enables camera-consistent video generation and editing operations that are difficult to achieve with existing models. Ultimately, our results establish a practical and scalable approach for bridging synthetic control and real-world photographic emulation.

cs.CV↗

arXiv2026

UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration

Universal image restoration aims to recover clean images from arbitrary real-world degradations using a single inference model. Despite significant progress, existing all-in-one restoration networks do not scale to multiple degradations. As the number of degradations increases, training becomes unstable, models grow excessively large, and performance drops across both seen and unseen domains. In this work, we show that scaling universal restoration is fundamentally limited by interference across degradations during joint learning, leading to catastrophic task forgetting. To address this challenge, we introduce a unified inference pipeline with a multi-branch mixture-of-experts architecture that decomposes restoration knowledge across specialized task-adaptable experts. Our approach enables scalable learning (over sixteen degradations), adapts and generalizes robustly to unseen domains, and supports user-controllable restoration across degradations. Beyond achieving superior performance across benchmarks, this work establishes a new design paradigm for scalable and controllable universal image restoration.

cs.CV↗

arXiv2025

Enabling High-Quality In-the-Wild Imaging from Severely Aberrated Metalens Bursts

We tackle the challenge of robust, in-the-wild imaging using ultra-thin nanophotonic metalens cameras. Meta-lenses, composed of planar arrays of nanoscale scatterers, promise dramatic reductions in size and weight compared to conventional refractive optics. However, severe chromatic aberration, pronounced light scattering, narrow spectral bandwidth, and low light efficiency continue to limit their practical adoption. In this work, we present an end-to-end solution for in-the-wild imaging that pairs a metalens several times thinner than conventional optics with a bespoke multi-image restoration framework optimized for practical metalens cameras. Our method centers on a lightweight convolutional network paired with a memory-efficient burst fusion algorithm that adaptively corrects noise, saturation clipping, and lens-induced distortions across rapid sequences of extremely degraded metalens captures. Extensive experiments on diverse, real-world handheld captures demonstrate that our approach consistently outperforms existing burst-mode and single-image restoration techniques.These results point toward a practical route for deploying metalens-based cameras in everyday imaging applications.

physics.optics↗

arXiv2025

Aberration Correcting Vision Transformers for High-Fidelity Metalens Imaging

Metalens is an emerging optical system with an irreplaceable merit in that it can be manufactured in ultra-thin and compact sizes, which shows great promise in various applications. Despite its advantage in miniaturization, its practicality is constrained by spatially varying aberrations and distortions, which significantly degrade the image quality. Several previous arts have attempted to address different types of aberrations, yet most of them are mainly designed for the traditional bulky lens and ineffective to remedy harsh aberrations of the metalens. While there have existed aberration correction methods specifically for metalens, they still fall short of restoration quality. In this work, we propose a novel aberration correction framework for metalens-captured images, harnessing Vision Transformers (ViT) that have the potential to restore metalens images with non-uniform aberrations. Specifically, we devise a Multiple Adaptive Filters Guidance (MAFG), where multiple Wiener filters enrich the degraded input images with various noise-detail balances and a cross-attention module reweights the features considering the different degrees of aberrations. In addition, we introduce a Spatial and Transposed self-Attention Fusion (STAF) module, which aggregates features from spatial self-attention and transposed self-attention modules to further ameliorate aberration correction. We conduct extensive experiments, including correcting aberrated images and videos, and clean 3D reconstruction. The proposed method outperforms the previous arts by a significant margin. We further fabricate a metalens and verify the practicality of our method by restoring the images captured with the manufactured metalens. Code and pre-trained models are available at https://benhenryl.github.io/Metalens-Transformer.

eess.IV↗

arXiv2025

UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations

Image restoration is essential for enhancing degraded images across computer vision tasks. However, most existing methods address only a single type of degradation (e.g., blur, noise, or haze) at a time, limiting their real-world applicability where multiple degradations often occur simultaneously. In this paper, we propose UniCoRN, a unified image restoration approach capable of handling multiple degradation types simultaneously using a multi-head diffusion model. Specifically, we uncover the potential of low-level visual cues extracted from images in guiding a controllable diffusion model for real-world image restoration and we design a multi-head control network adaptable via a mixture-of-experts strategy. We train our model without any prior assumption of specific degradations, through a smartly designed curriculum learning recipe. Additionally, we also introduce MetaRestore, a metalens imaging benchmark containing images with multiple degradations and artifacts. Extensive evaluations on several challenging datasets, including our benchmark, demonstrate that our method achieves significant performance gains and can robustly restore images with severe degradations. Project page: https://codejaeger.github.io/unicorn-gh

cs.CV↗

arXiv2022

Superior-catalytic performance of Ni-Co Layered double hydroxide nanosheets for the reduction of p-nitrophenol

Layered double-hydroxides (LDHs) are superior to the conventional (Transition Metal Oxides) TMOs as their lamellar morphology accommodates higher active sites contributing to the facile electron transfer towards the material degradation relations, thus attracts an immense attention for catalysis application. Moreover, the high catalytic activity of LDHs is linked to their facile anion exchange, specific electronic structures, and versatile chemical compositions. Recently, LDHs with bimetallic or ternary combinations are preferably used for hydrogenation of p-nitrophenol, a toxic and carcinogenic pollutant commonly found in industrial wastewater. Herein, a cost-effective co-precipitation fabrication protocol to obtain Ni-Co layered double hydroxide is proposed. The well-defined arrangement of active sites in the 2D structure of LDH, and the synergistic catalytic effect of Ni and Co greatly improves the efficiency for the conversion of p-nitrophenol (p-NP) to p-aminophenol (p-AMP). The catalytic performance at higher temperatures is also shown. The obtained results are further extended to explore the advantage of Ni-Co LDH as an electrocatalyst for Hydrogen Evolution Reaction (HER).

cond-mat.mtrl-sci↗

arXiv2022

Role of porosity and diffusion coefficient in porous electrode used in supercapacitors- Correlating theoretical and experimental studies

Porous electrodes are fast emerging as essential components for next generation supercapacitors. Using porous structures of Co3O4, Mn3O4, alpha Fe2O3, and carbon, their advantages over the solid counterpart is unequivocally established. The improved performance in porous architecture is linked to the enhanced active specific surface and direct channels leading to improved electrolyte interaction with the redox active sites. A theoretical model utilizing the Fick's law is proposed, that can consistently explain the experimental data. The porous structures exhibit nearly 50 - 80 percentage increment in specific capacitance, along with high rate capabilities and excellent cycling stability due to the higher diffusion coefficients.

cond-mat.mtrl-sci↗

arXiv2011

Extension of Fuzzy h-ideals in $Γ$-hemirings

In this paper the concept of the extension of fuzzy h-ideals in one-sided $Γ$-hemiring is introduced and some of its properties are investigated. Specially we have studied the extension of prime fuzzy h-ideals in $Γ$-hemirings and gave its characterization.

math.GM↗