This study presents the outcomes of the first Controllable Bokeh Rendering Challenge at NTIRE and highlights the most effective submitted methodologies. In total, 44 participants registered for the competition, of which 8 teams submitted valid solutions after the conclusion of the final test phase. All submissions were evaluated on unseen images, focusing on portraits and intricate subjects with complex and visually appealing bokeh phenomena. In addition to the first track focusing on established quantitative fidelity metrics, we conducted a qualitative user study with a panel of experts for a second track focusing on perceptual assessment. As this was the inaugural challenge on this topic, most of the participants focused on refining and extending the Bokehlicious baseline method.

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. We build on RealDefocus, a benchmark derived from the real-world RealBokeh dataset originally proposed for Bokeh Rendering. RealDefocus provides paired defocused inputs and sharp ground truth images, predefined training/validation/test splits, and a unified evaluation framework for comparing image restoration and neural rendering approaches. We further outline a benchmarking protocol with cross-dataset validation to assess reconstruction quality and generalization. The project page is publicly available at: www.github.com/TimSeizinger/RealDefocus-Benchmark.

Bokeh rendering methods play a key role in creating the visually appealing, softly blurred backgrounds seen in professional photography. While recent learning-based approaches show promising results, generating realistic Bokeh with variable strength remains challenging. Existing methods require additional inputs and suffer from unrealistic Bokeh reproduction due to reliance on synthetic data. In this work, we propose Bokehlicious, a highly efficient network that provides intuitive control over Bokeh strength through an Aperture-Aware Attention mechanism, mimicking the physical lens aperture. To further address the lack of high-quality real-world data, we present RealBokeh, a novel dataset featuring 23,000 high-resolution (24-MP) images captured by professional photographers, covering diverse scenes with varied aperture and focal length settings. Evaluations on both our new RealBokeh and established Bokeh rendering benchmarks show that Bokehlicious consistently outperforms SOTA methods while significantly reducing computational cost and exhibiting strong zero-shot generalization. Our method and dataset further extend to defocus deblurring, achieving competitive results on the RealDOF benchmark. Our code and data can be found at https://github.com/TimSeizinger/Bokehlicious

This work examines the findings of the NTIRE 2025 Shadow Removal Challenge. A total of 306 participants have registered, with 17 teams successfully submitting their solutions during the final evaluation phase. Following the last two editions, this challenge had two evaluation tracks: one focusing on reconstruction fidelity and the other on visual perception through a user study. Both tracks were evaluated with images from the WSRD+ dataset, simulating interactions between self- and cast-shadows with a large number of diverse objects, textures, and materials.

Illumination in practical scenarios is inherently complex, involving colored light sources, occlusions, and diverse material interactions that produce intricate reflectance and shading effects. However, existing methods often oversimplify this challenge by assuming a single light source or uniform, white-balanced lighting, leaving many of these complexities unaddressed.In this paper, we introduce CL3AN, the first large-scale, high-resolution dataset of its kind designed to facilitate the restoration of images captured under multiple Colored Light sources to their Ambient-Normalized counterparts. Through benchmarking, we find that leading approaches often produce artifacts, such as illumination inconsistencies, texture leakage, and color distortion, primarily due to their limited ability to precisely disentangle illumination from reflectance. Motivated by this insight, we achieve such a desired decomposition through a novel learning framework that leverages explicit chromaticity and luminance components guidance, drawing inspiration from the principles of the Retinex model. Extensive evaluations on existing benchmarks and our dataset demonstrate the effectiveness of our approach, showcasing enhanced robustness under non-homogeneous color lighting and material-specific reflectance variations, all while maintaining a highly competitive computational cost. The benchmark, codes, and models are available at www.github.com/fvasluianu97/RLN2.

This report presents an overview of the NTIRE 2025 Ambient Lighting Normalization Challenge, a competition designed to advance techniques for improving image consistency under varying lighting conditions. Participants were tasked with developing algorithms capable of normalizing images acquired under various direct lighting systems to ambient lighting equivalents while preserving image quality, detail, and color accuracy. With a total number of 171 participants, the first edition of the challenge resulted in a number of 10 Final Phase submissions, which are part of the challenge benchmark. Conditions such as image restoration fidelity and the perceptual quality of the normalized outputs form the base of the proposed ranking. A user study including subjects with various backgrounds, including professional photographers, is backing the proposed ranking, emphasizing clearly the topperforming solutions. This report outlines the competition framework, dataset composition, evaluation metrics, and performance of different approaches. The top-performing methods leveraged deep learning strategies, using both end-to-end learning techniques and solutions based on iterative refinement. A comparative analysis of submissions highlights the strengths and limitations of each approach, offering insights into the effectiveness of all proposed ambient lighting normalization strategies.

Lighting normalization is a crucial but underexplored restoration task with broad applications. However, existing works often simplify this task within the context of shadow removal, limiting the light sources to one and oversimplifying the scene, thus excluding complex self-shadows and restricting surface classes to smooth ones. Although promising, such simplifications hinder generalizability to more realistic settings encountered in daily use. In this paper, we propose a new challenging task termed Ambient Lighting Normalization (ALN), which enables the study of interactions between shadows, unifying image restoration and shadow removal in a broader context. To address the lack of appropriate datasets for ALN, we introduce the large-scale high-resolution dataset Ambient6K, comprising samples obtained from multiple light sources and including self-shadows resulting from complex geometries, which is the first of its kind. For benchmarking, we select various mainstream methods and rigorously evaluate them on Ambient6K. Additionally, we propose IFBlend, a novel strong baseline that maximizes Image-Frequency joint entropy to selectively restore local areas under different lighting conditions, without relying on shadow localization priors. Experiments show that IFBlend achieves SOTA scores on Ambient6K and exhibits competitive performance on conventional shadow removal benchmarks compared to shadow-specific models with mask priors. The dataset, benchmark, and code are available at https://github.com/fvasluianu97/IFBlend.

This work reviews the results of the NTIRE 2024 Challenge on Shadow Removal. Building on the last year edition, the current challenge was organized in two tracks, with a track focused on increased fidelity reconstruction, and a separate ranking for high performing perceptual quality solutions. Track 1 (fidelity) had 214 registered participants, with 17 teams submitting in the final phase, while Track 2 (perceptual) registered 185 participants, resulting in 18 final phase submissions. Both tracks were based on data from the WSRD dataset, simulating interactions between self-shadows and cast shadows, with a large variety of represented objects, textures, and materials. Improved image alignment enabled increased fidelity reconstruction, with restored frames mostly indistinguishable from the references images for top performing solutions.

Many advancements of mobile cameras aim to reach the visual quality of professional DSLR cameras. Great progress was shown over the last years in optimizing the sharp regions of an image and in creating virtual portrait effects with artificially blurred backgrounds. Bokeh is the aesthetic quality of the blur in out-of-focus areas of an image. This is a popular technique among professional photographers, and for this reason, a new goal in computational photography is to optimize the Bokeh effect itself.This paper introduces EBokehNet, a efficient state-of-the-art solution for Bokeh effect transformation and rendering. Our method can render Bokeh from an all-in-focus image, or transform the Bokeh of one lens to the effect of another lens without harming the sharp foreground regions in the image. Moreover we can control the shape and strength of the effect by feeding the lens properties i.e. type (Sony or Canon) and aperture, into the neural network as an additional input. Our method is a winning solution at the NTIRE 2023 Lens-to-Lens Bokeh Effect Transformation Challenge, and state-of-the-art at the EBB benchmark.

Shadow removal is an important computer vision task, whose aim is to successfully detect the shadow affected area appearing through light occlussion, followed by a photorealistic restoration of the affected image contents, textures, and details. After decades of research, a multitude of hand-crafted restoration techniques were proposed, following different observations on shadow formation models, with scenes altered in particular conditions. However, the increased popularity of deep learning based solutions enabled a significant step forward for the shadow removal solutions, both in terms of reconstruction fidelity and perceptual properties. However, the publicly available datasets remain focused around a particularly low complexity setup, with a low variety of light occluders and affected backgrounds, and with limited representation for more complex light interactions and complex shadow patterns. In this work, we propose WSRD, a novel benchmark for high resolution image shadow removal, characterized by a large variety in terms or represented objects, backgrounds and light occluders. We study more complex interactions, combining self shadows with externally casted shadows, to further extend the study of the phenomenon, its factors and effects. To prove WSRD as a relevant benchmark, we propose DNSR, a novel shadow removal method, comparing the results on WSRD with the performance level observed on other well-established benchmarks like ISTD and ISTD+. We validate our approach comparing with existing state-of-the-art (SOTA) methods, improving both in reconstruction fidelity and perceptual properties, setting a new SOTA for the field.

This paper presents a review of the NTIRE 2023 challenge on night photography rendering. The goal of the challenge was to find solutions that process raw camera images taken in nighttime conditions conditions, and thereby produce a photo-quality output images in the standard RGB (sRGB) space. Unlike the previous year’s competition, participants were not provided with a large training dataset for the target sensor. Instead, this time they were given images of a color checker illuminated by a known light source. To evaluate the results, a sufficient number of viewers were asked to assess the visual quality of the proposed solutions, considering the subjective nature of the task. The highest ranking solutions were further ranked by Richard Collins, a renowned photographer. The top ranking participants’ solutions effectively represent the state-of-the-art in nighttime photography rendering. More results can be found at https://nightimaging.org/

We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge. Recent advancements of mobile photography aim to reach the visual quality of full-frame cameras. Now, a goal in computational photography is to optimize the Bokeh effect itself, which is the aesthetic quality of the blur in out-of-focus areas of an image. Photographers create this aesthetic effect by benefiting from the lens optical properties.The aim of this work is to design a neural network capable of converting the the Bokeh effect of one lens to the effect of another lens without harming the sharp foreground regions in the image. For a given input image, knowing the target lens type, we render or transform the Bokeh effect accordingly to the lens properties. We build the BETD using two full-frame Sony cameras, and diverse lens setups.To the best of our knowledge, we are the first attempt to solve this novel task, and we provide the first BETD dataset and benchmark for it. The challenge had 99 registered participants. The submitted methods gauge the state-of-the-art in Bokeh effect rendering and transformation.