Current text-to-image diffusion models excel at generating diverse, high-quality images, yet they struggle to incorporate fine-grained camera metadata such as precise aperture settings. In this work, we introduce a novel text-to-image diffusion framework that leverages camera metadata, or EXIF data, which is often embedded in image files, with an emphasis on generating controllable lens blur. Our method mimics the physical image formation process by first generating an all-in-focus image, estimating its monocular depth, predicting a plausible focus distance with a novel focus distance transformer, and then forming a defocused image with an existing differentiable lens blur model [32]. Gradients flow backwards through this whole process, allowing us to learn without explicit supervision to generate defocus effects based on content elements and the provided EXIF data. At inference time, this enables precise interactive user control over defocus effects while preserving scene contents, which is not achievable with existing diffusion models. Experimental results demonstrate that our model enables superior fine-grained control without altering the depicted scene.

This paper introduces a novel dataset construction pipeline that samples pairs of frames from videos and uses multimodal large language models (MLLMs) to generate editing instructions for training instruction-based image manipulation models. Video frames inherently preserve the identity of subjects and scenes, ensuring consistent content preservation during editing. Additionally, video data captures diverse, natural dynamics—such as non-rigid subject motion and complex camera movements—that are difficult to model otherwise, making it an ideal source for scalable dataset construction. Using this approach, we create a new dataset to train InstructMove, a model capable of instruction-based complex manipulations that are difficult to achieve with synthetically generated datasets. Our model demonstrates state-of-the-art performance in tasks such as adjusting subject poses, rearranging elements, and altering camera perspectives. The project page is available here.

While consumer displays increasingly support more than 10 stops of dynamic range, most image assets — such as internet photographs and generative AI content — remain limited to 8-bit low dynamic range (LDR), constraining their utility across high dynamic range (HDR) applications. Currently, no generative model can produce high-bit, high-dynamic range content in a generalizable way. Existing LDR-to-HDR conversion methods often struggle to produce photorealistic details and physically-plausible dynamic range in the clipped areas. We introduce LEDiff, a method that enables a generative model with HDR content generation through latent space fusion inspired by image-space exposure fusion techniques. It also functions as an LDR-to-HDR converter, expanding the dynamic range of existing low-dynamic range images. Our approach uses a small HDR dataset to enable a pretrained diffusion model to recover detail and dynamic range in clipped highlights and shadows. LEDiff brings HDR capabilities to existing generative models and converts any LDR image to HDR, creating photorealistic HDR outputs for image generation, image-based lighting (HDR environment map generation), and photographic effects such as depth of field simulation, where linear HDR data is essential for realistic quality.

Focus is a cornerstone of photography, yet autofocus systems often fail to capture the intended subject, and users frequently wish to adjust focus after capture. We introduce a novel method for realistic post-capture refocusing using video diffusion models. From a single defocused image, our approach generates a perceptually accurate focal stack, represented as a video sequence, enabling interactive refocusing and unlocking a range of downstream applications. We release a large-scale focal stack dataset acquired under diverse real-world smartphone conditions to support this work and future research. Our method consistently outperforms existing approaches in both perceptual quality and robustness across challenging scenarios, paving the way for more advanced focus-editing capabilities in everyday photography. Code and data are available at www.learn2refocus.github.io

Optical blur is an inherent property of any lens system and is challenging to model in modern cameras because of their complex optical elements. To tackle this challenge, we introduce a high-dimensional neural representation of blur-the lens blur field-and a practical method for acquiring it. The lens blur field is a multilayer perceptron (MLP) designed to (1) accurately capture variations of the lens 2D point spread function over image plane location, focus setting and, optionally, depth and (2) represent these variations parametrically as a single, sensor-specific function. The representation models the combined effects of defocus, diffraction, aberration, and accounts for sensor features such as pixel color filters and pixel-specific micro-lenses. To learn the real-world blur field of a given device, we formulate a generalized non-blind deconvolution problem that directly optimizes the MLP weights using a small set of focal stacks as the only input. We also provide a first-of-its-kind dataset of 5D blur fields-for smartphone cameras, camera bodies equipped with a variety of lenses, etc. Lastly, we show that acquired 5D blur fields are expressive and accurate enough to reveal, for the first time, differences in optical behavior of smartphone devices of the same make and model.

The inherent generative power of denoising diffusion mod-els makes them well-suited for image restoration tasks where the objective is to find the optimal high-quality image within the generative space that closely resembles the input im-age. We propose a method to adapt a pretrained diffusion model for image restoration by simply adding noise to the input image to be restored and then denoise. Our method is based on the observation that the space of a generative model needs to be constrained. We impose this constraint by finetuning the generative model with a set of anchor images that capture the characteristics of the input image. With the constrained space, we can then leverage the sampling strat-egy used for generation to do image restoration. We evaluate against previous methods and show superior performances on multiple real-world restoration datasets in preserving identity and image quality. We also demonstrate an important and practical application on personalized restoration, where we use a personal album as the anchor images to constrain the generative space. This approach allows us to produce results that accurately preserve high-frequency details, which previous works are unable to do. Project webpage: https://gen2res.github.io.

At the core of portrait photography is the search for ideal lighting and viewpoint. The process often requires advanced knowledge in photography and an elaborate studio setup. In this work, we propose Holo-Relighting, a volumetric relighting method that is capable of synthesizing novel viewpoints, and novel lighting from a single image. Holo-Relighting leverages the pretrained 3D GAN (EG3D) to reconstruct geometry and appearance from an input portrait as a set of 3D-aware features. We design a relighting module conditioned on a given lighting to process these features, and predict a relit 3D representation in the form of a tri-plane, which can render to an arbitrary viewpoint through volume rendering. Besides viewpoint and lighting control, Holo-Relighting also takes the head pose as a condition to enable head-pose-dependent lighting effects. With these novel designs, Holo-Relighting can generate complex non-Lambertian lighting effects (e.g., specular highlights and cast shadows) without using any explicit physical lighting priors. We train Holo-Relighting with data captured with a light stage, and propose two data-rendering techniques to improve the data quality for training the volumetric relighting system. Through quantitative and qualitative experiments, we demonstrate Holo-Relighting can achieve state-of-the-arts relighting quality with better photorealism, 3D consistency and controllability.

Bokeh is widely used in photography to draw attention to the subject while effectively isolating distractions in the background. Computational methods can simulate bokeh effects without relying on a physical camera lens, but the inaccurate lens modeling in existing filtering-based meth-ods leads to artifacts that need post-processing or learning-based methods to fix. We propose Dr.Bokeh, a novel ren-dering method that addresses the issue by directly correcting the defect that violates physics in the current filtering-based bokeh rendering equation. Dr.Bokeh first preprocesses the input RGBD to obtain a layered scene representation. Dr.Bokeh then takes the layered representation and user-defined lens parameters to render photo-realistic lens blur based on the novel occlusion-aware bokeh rendering method. Experiments show that the non-learning based renderer Dr.Bokeh outperforms state-of-the-art bokeh ren-dering algorithms in terms of photo-realism. In addition, extensive quantitative and qualitative evaluations show that the more accurate lens model pushes the limit of depth-from-defocus.

Wires and powerlines are common visual distractions that often undermine the aesthetics of photographs. The manual process of precisely segmenting and removing them is extremely tedious and may take up hours, especially on high-resolution photos where wires may span the entire space. In this paper, we present an automatic wire clean-up system that eases the process of wire segmentation and removal/inpainting to within a few seconds. We observe several unique challenges: wires are thin, lengthy, and sparse. These are rare properties of subjects that common segmentation tasks cannot handle, especially in high-resolution images. We thus propose a two-stage method that leverages both global and local contexts to accurately segment wires in high-resolution images efficiently, and a tile-based inpainting strategy to remove the wires given our predicted segmentation masks. We also introduce the first wire segmentation benchmark dataset, WireSegHR. Finally, we demonstrate quantitatively and qualitatively that our wire clean-up system enables fully automated wire removal with great generalization to various wire appearances.

We address the problem of learning person-specific facial priors from a small number (e.g., 20) of portrait photos of the same person. This enables us to edit this specific person's facial appearance, such as expression and lighting, while preserving their identity and high-frequency facial details. Key to our approach, which we dub DiffusionRig, is a diffusion model conditioned on, or “rigged by,“ crude 3D face models estimated from single in-the-wild images by an off-the-shelf estimator. On a high level, DiffusionRig learns to map simplistic renderings of 3D face models to realistic photos of a given person. Specifically, DiffusionRig is trained in two stages: It first learns generic facial priors from a large-scale face dataset and then person-specific priors from a small portrait photo collection of the person of interest. By learning the CGI-to-photo mapping with such personalized priors,DiffusionRig can “rig“ the lighting, facial expression, head pose, etc. of a portrait photo, conditioned only on coarse 3D models while preserving this person's identity and other high-frequency characteristics. Qualitative and quantitative experiments show that DiffusionRig outperforms existing approaches in both identity preservation and photorealism. Please see the project website: https://diffusionrig.github.io for the supplemental material, video, code, and data.

Recent portrait relighting methods have achieved realistic results of portrait lighting effects given a desired lighting representation such as an environment map. However, these methods are not intuitive for user interaction and lack precise lighting control. We introduce LightPainter, a scribble-based relighting system that allows users to interactively manipulate portrait lighting effect with ease. This is achieved by two conditional neural networks, a delighting module that recovers geometry and albedo optionally conditioned on skin tone, and a scribble-based module for re-lighting. To train the relighting module, we propose a novel scribble simulation procedure to mimic real user scribbles, which allows our pipeline to be trained without any human annotations. We demonstrate high-quality and flexible portrait lighting editing capability with both quantitative and qualitative experiments. User study comparisons with commercial lighting editing tools also demonstrate consistent user preference for our method.

A light stage uses a series of calibrated cameras and lights to capture a subject's facial appearance under varying illumination and viewpoint. This captured information is crucial for facial reconstruction and relighting. Unfortunately, light stages are often inaccessible: they are expensive and require significant technical expertise for construction and operation. In this paper, we present SunStage: a lightweight alternative to a light stage that captures comparable data using only a smartphone camera and the sun. Our method only requires the user to capture a selfie video outdoors, rotating in place, and uses the varying angles between the sun and the face as guidance in joint reconstruction of facial geometry, reflectance, camera pose, and lighting parameters. Despite the in-the-wild un-calibrated setting, our approach is able to reconstruct detailed facial appearance and geometry, enabling compelling effects such as relighting, novel view synthesis, and reflectance editing.

Modern smartphones can continuously stream multi-megapixel RGB images at 60 Hz, synchronized with high-quality 3D pose information and low-resolution LiDAR-driven depth estimates. During a snapshot photograph, the natural unsteadiness of the photographer's hands offers millimeter-scale variation in camera pose, which we can capture along with RGB and depth in a circular buffer. In this work we explore how, from a bundle of these measurements acquired during viewfinding, we can combine dense micro-baseline parallax cues with kilopixel LiDAR depth to distill a high-fidelity depth map. We take a test-time optimization approach and train a coordinate MLP to output photometrically and geometrically consistent depth estimates at the continuous coordinates along the path traced by the photographer's natural hand shake. With no additional hardware, artificial hand motion, or user interaction beyond the press of a button, our proposed method brings high-resolution depth estimates to point-and-shoot “table-top” photography – textured objects at close range.

Image processing pipelines are ubiquitous and we rely on them either directly, by filtering or adjusting an image post-capture, or indirectly, as image signal processing (ISP) pipelines on broadly deployed camera systems. Used by artists, photographers, system engineers, and for downstream vision tasks, traditional image processing pipelines feature complex algorithmic branches developed over decades. Recently, image-to-image networks have made great strides in image processing, style transfer, and semantic understanding. The differentiable nature of these networks allows them to fit a large corpus of data; however, they do not allow for intuitive, fine-grained controls that photographers find in modern photo-finishing tools. This work closes that gap and presents an approach to making complex photo-finishing pipelines differentiable, allowing legacy algorithms to be trained akin to neural networks using first-order optimization methods. By concatenating tailored network proxy models of individual processing steps (e.g. white-balance, tone-mapping, color tuning), we can model a non-differentiable reference image finishing pipeline more faithfully than existing proxy image-to-image network models. We validate the method for several diverse applications, including photo and video style transfer, slider regression for commercial camera ISPs, photography-driven neural demosaicking, and adversarial photo-editing.

Traditional reflection removal algorithms either use a single image as input, which suffers from intrinsic ambiguities, or use multiple images from a moving camera, which is inconvenient for users. We instead propose a learning-based dereflection algorithm that uses stereo images as input. This is an effective trade-off between the two extremes: the parallax between two views provides cues to remove reflections, and two views are easy to capture due to the adoption of stereo cameras in smartphones. Our model consists of a learning-based reflection-invariant flow model for dual-view registration, and a learned synthesis model for combining aligned image pairs. Because no dataset for dual-view reflection removal exists, we render a synthetic dataset of dual-views with and without reflections for use in training. Our evaluation on an additional real-world dataset of stereo pairs shows that our algorithm outperforms existing single-image and multi-image dereflection approaches.

Many historical people were only ever captured by old, faded, black and white photos, that are distorted due to the limitations of early cameras and the passage of time. This paper simulates traveling back in time with a modern camera to rephotograph famous subjects. Unlike conventional image restoration filters which apply independent operations like denoising, colorization, and superresolution, we leverage the StyleGAN2 framework to project old photos into the space of modern high-resolution photos, achieving all of these effects in a unified framework. A unique challenge with this approach is retaining the identity and pose of the subject in the original photo, while discarding the many artifacts frequently seen in low-quality antique photos. Our comparisons to current state-of-the-art restoration filters show significant improvements and compelling results for a variety of important historical people. Please go to time-travell-rephotography.github.io for many more results.

Casually-taken portrait photographs often suffer from unflattering lighting and shadowing because of suboptimal conditions in the environment. Aesthetic qualities such as the position and softness of shadows and the lighting ratio between the bright and dark parts of the face are frequently determined by the constraints of the environment rather than by the photographer. Professionals address this issue by adding light shaping tools such as scrims, bounce cards, and flashes. In this paper, we present a computational approach that gives casual photographers some of this control, thereby allowing poorly-lit portraits to be relit post-capture in a realistic and easily-controllable way. Our approach relies on a pair of neural networks---one to remove foreign shadows cast by external objects, and another to soften facial shadows cast by the features of the subject and to add a synthetic fill light to improve the lighting ratio. To train our first network we construct a dataset of real-world portraits wherein synthetic foreign shadows are rendered onto the face, and we show that our network learns to remove those unwanted shadows. To train our second network we use a dataset of Light Stage scans of human subjects to construct input/output pairs of input images harshly lit by a small light source, and variably softened and fill-lit output images of each face. We propose a way to explicitly encode facial symmetry and show that our dataset and training procedure enable the model to generalize to images taken in the wild. Together, these networks enable the realistic and aesthetically pleasing enhancement of shadows and lights in real-world portrait images. 1

This paper shows that when applying machine learning to digital zoom, it is beneficial to operate on real, RAW sensor data. Existing learning-based super-resolution methods do not use real sensor data, instead operating on processed RGB images. We show that these approaches forfeit detail and accuracy that can be gained by operating on raw data, particularly when zooming in on distant objects. The key barrier to using real sensor data for training is that ground-truth high-resolution imagery is missing. We show how to obtain such ground-truth data via optical zoom and contribute a dataset, SR-RAW, for real-world computational zoom. We use SR-RAW to train a deep network with a novel contextual bilateral loss that is robust to mild misalignment between input and outputs images. The trained network achieves state-of-the-art performance in 4X and 8X computational zoom. We also show that synthesizing sensor data by resampling high-resolution RGB images is an oversimplified approximation of real sensor data and noise, resulting in worse image quality.

In cinema, large camera lenses create beautiful shallow depth of field (DOF), but make focusing difficult and expensive. Accurate cinema focus usually relies on a script and a person to control focus in realtime. Casual videographers often crave cinematic focus, but fail to achieve it. We either sacrifice shallow DOF, as in smartphone videos; or we struggle to deliver accurate focus, as in videos from larger cameras. This paper is about a new approach in the pursuit of cinematic focus for casual videography. We present a system that synthetically renders refocusable video from a deep DOF video shot with a smartphone, and analyzes future video frames to deliver context-aware autofocus for the current frame. To create refocusable video, we extend recent machine learning methods designed for still photography, contributing a new dataset for machine training, a rendering model better suited to cinema focus, and a filtering solution for temporal coherence. To choose focus accurately for each frame, we demonstrate autofocus that looks at upcoming video frames and applies AI-assist modules such as motion, face, audio and saliency detection. We also show that autofocus benefits from machine learning and a large-scale video dataset with focus annotation, where we use our RVR-LAAF GUI to create this sizable dataset efficiently. We deliver, for example, a shallow DOF video where the autofocus transitions onto each person before she begins to speak. This is impossible for conventional camera autofocus because it would require seeing into the future.

We present an approach to separating reflection from a single image. The approach uses a fully convolutional network trained end-to-end with losses that exploit low-level and high-level image information. Our loss function includes two perceptual losses: a feature loss from a visual perception network, and an adversarial loss that encodes characteristics of images in the transmission layers. We also propose a novel exclusion loss that enforces pixel-level layer separation. We create a dataset of real-world images with reflection and corresponding ground-truth transmission layers for quantitative evaluation and model training. We validate our method through comprehensive quantitative experiments and show that our approach outperforms state-of-the-art reflection removal methods in PSNR, SSIM, and perceptual user study. We also extend our method to two other image enhancement tasks to demonstrate the generality of our approach.

Abstract Videos captured by consumer cameras often exhibit temporal variations in color and tone that are caused by camera auto‐adjustments like white‐balance and exposure. When such videos are sub‐sampled to play fast‐forward, as in the increasingly popular forms of timelapse and hyperlapse videos, these temporal variations are exacerbated and appear as visually disturbing high frequency flickering. Previous techniques to photometrically stabilize videos typically rely on computing dense correspondences between video frames, and use these correspondences to remove all color changes in the video sequences. However, this approach is limited in fast‐forward videos that often have large content changes and also might exhibit changes in scene illumination that should be preserved. In this work, we propose a novel photometric stabilization algorithm for fast‐forward videos that is robust to large content‐variation across frames. We compute pairwise color and tone transformations between neighboring frames and smooth these pair‐wise transformations while taking in account the possibility of scene/content variations. This allows us to eliminate high‐frequency fluctuations, while still adapting to real variations in scene characteristics. We evaluate our technique on a new dataset consisting of controlled synthetic and real videos, and demonstrate that our techniques outperforms the state‐of‐the‐art.