Wolfgang Heidrich

Xinge Yang, Qiang Fu, Wolfgang Heidrich

Deep optical optimization has recently emerged as a new paradigm for designing computational imaging systems using only the output image as the objective. However, it has been limited to either simple optical systems consisting of a single element such as a diffractive optical element (DOE) or metalens, or the fine-tuning of compound lenses from good initial designs. Here we present a DeepLens design method based on curriculum learning, which is able to learn optical designs of compound lenses ab initio from randomly initialized surfaces without human intervention, therefore overcoming the need for a good initial design. We demonstrate the effectiveness of our approach by fully automatically designing both classical imaging lenses and a large field-of-view extended depth-of-field computational lens in a cellphone-style form factor, with highly aspheric surfaces and a short back focal length.

Xinge Yang, Qiang Fu, Mohammed Elhoseiny et al.

Computer vision methods for depth estimation usually use simple camera models with idealized optics. For modern machine learning approaches, this creates an issue when attempting to train deep networks with simulated data, especially for focus-sensitive tasks like Depth-from-Focus. In this work, we investigate the domain gap caused by off-axis aberrations that will affect the decision of the best-focused frame in a focal stack. We then explore bridging this domain gap through aberration-aware training (AAT). Our approach involves a lightweight network that models lens aberrations at different positions and focus distances, which is then integrated into the conventional network training pipeline. We evaluate the generality of pretrained models on both synthetic and real-world data. Our experimental results demonstrate that the proposed AAT scheme can improve depth estimation accuracy without fine-tuning the model or modifying the network architecture.

Matheus Souza, Wolfgang Heidrich

Image signal processors (ISPs) are historically grown legacy software systems for reconstructing color images from noisy raw sensor measurements. They are usually composited of many heuristic blocks for denoising, demosaicking, and color restoration. Color reproduction in this context is of particular importance, since the raw colors are often severely distorted, and each smart phone manufacturer has developed their own characteristic heuristics for improving the color rendition, for example of skin tones and other visually important colors. In recent years there has been strong interest in replacing the historically grown ISP systems with deep learned pipelines. Much progress has been made in approximating legacy ISPs with such learned models. However, so far the focus of these efforts has been on reproducing the structural features of the images, with less attention paid to color rendition. Here we present CRISPnet, the first learned ISP model to specifically target color rendition accuracy relative to a complex, legacy smart phone ISP. We achieve this by utilizing both image metadata (like a legacy ISP would), as well as by learning simple global semantics based on image classification -- similar to what a legacy ISP does to determine the scene type. We also contribute a new ISP image dataset consisting of both high dynamic range monitor data, as well as real-world data, both captured with an actual cell phone ISP pipeline under a variety of lighting conditions, exposure times, and gain settings.

Yidan Zheng, Matheus Souza, Kaizhang Kang et al.

We present a real-time gaze tracking system that directly acquires task-relevant latent features using a fully passive optical encoder. Instead of forming and processing full-resolution images, our approach leverages a microlens array with a co-designed binary chromium mask to perform spatially multiplexed optical encoding, producing a compact set of measurements sufficient for gaze estimation. By integrating sensing and feature extraction in the optical domain, the proposed system eliminates the need for high-bandwidth image readout and substantially reduces computational overhead. The encoded measurements are captured by a 4 x 4 phototransistor array and mapped to gaze direction using a lightweight neural network. Our proof-of-concept prototype enables an end-to-end sensing-to-inference latency of 3.4 ms, outperforming published research systems. We demonstrate the effectiveness of our approach on both simulated and real-world data, achieving competitive gaze estimation accuracy while significantly improving latency and energy efficiency compared to conventional camera-based pipelines. This work highlights the potential of task-driven optical sensing for ultra-low-latency, computationally efficient human-computer interaction systems.

Qiang Fu, Matheus Souza, Eunsue Choi et al.

Hyperspectral imaging empowers machine vision systems with the distinct capability of identifying materials through recording their spectral signatures. Recent efforts in data-driven spectral reconstruction aim at extracting spectral information from RGB images captured by cost-effective RGB cameras, instead of dedicated hardware. Published work reports exceedingly high numerical scores for this reconstruction task, yet real-world performance lags substantially behind. We systematically analyze the performance of such methods. First, we evaluate the overfitting limitations with respect to current datasets by training the networks with less data, validating the trained models with unseen yet slightly modified data and cross-dataset validation. Second, we reveal fundamental limitations in the ability of RGB to spectral methods to deal with metameric or near-metameric conditions, which have so far gone largely unnoticed due to the insufficiencies of existing datasets. We validate the trained models with metamer data generated by metameric black theory and re-training the networks with various forms of metamers. This methodology can also be used for data augmentation as a partial mitigation of the dataset issues, although the RGB to spectral inverse problem remains fundamentally ill-posed. Finally, we analyze the potential for modifying the problem setting to achieve better performance by exploiting optical encoding provided by either optical aberrations or deliberate optical design. Our experiments show such approaches provide improved results under certain circumstances, but their overall performance is limited by the same dataset issues. We conclude that future progress on snapshot spectral imaging will heavily depend on the generation of improved datasets which can then be used to design effective optical encoding strategies. Code: https://github.com/vccimaging/OpticsAwareHSI-Analysis.

Matheus Souza, Yidan Zheng, Kaizhang Kang et al.

Digital imaging systems have traditionally relied on brute-force measurement and processing of pixels arranged on regular grids. In contrast, the human visual system performs significant data reduction from the large number of photoreceptors to the optic nerve, effectively encoding visual information into a low-bandwidth latent space representation optimized for brain processing. Inspired by this, we propose a similar approach to advance artificial vision systems. Latent Space Imaging introduces a new paradigm that combines optics and software to encode image information directly into the semantically rich latent space of a generative model. This approach substantially reduces bandwidth and memory demands during image capture and enables a range of downstream tasks focused on the latent space. We validate this principle through an initial hardware prototype based on a single-pixel camera. By implementing an amplitude modulation scheme that encodes into the generative model's latent space, we achieve compression ratios ranging from 1:100 to 1:1000 during imaging, and up to 1:16384 for downstream applications. This approach leverages the model's intrinsic linear boundaries, demonstrating the potential of latent space imaging for highly efficient imaging hardware, adaptable future applications in high-speed imaging, and task-specific cameras with significantly reduced hardware complexity.

Simeng Qiu, Hadi Amata, Wolfgang Heidrich

Directional information measurement has many applications in domains such as robotics, virtual and augmented reality, and industrial computer vision. Conventional methods either require pre-calibration or necessitate controlled environments. The state-of-the-art MoireTag approach exploits the Moire effect and QR-design to continuously track the angular shift precisely. However, it is still not a fully QR code design. To overcome the above challenges, we propose a novel snapshot method for discrete angular measurement and tracking with scannable QR-design patterns that are generated by binary structures printed on both sides of a glass plate. The QR codes, resulting from the parallax effect due to the geometry alignment between two layers, can be readily measured as angular information using a phone camera. The simulation results show that the proposed non-contact object tracking framework is computationally efficient with high accuracy.

Xinge Yang, Chuong Nguyen, Wenbin Wang et al.

Modern cameras with large apertures often suffer from a shallow depth of field, resulting in blurry images of objects outside the focal plane. This limitation is particularly problematic for fixed-focus cameras, such as those used in smart glasses, where adding autofocus mechanisms is challenging due to form factor and power constraints. Due to unmatched optical aberrations and defocus properties unique to each camera system, deep learning models trained on existing open-source datasets often face domain gaps and do not perform well in real-world settings. In this paper, we propose an efficient and scalable dataset synthesis approach that does not rely on fine-tuning with real-world data. Our method simultaneously models depth-dependent defocus and spatially varying optical aberrations, addressing both computational complexity and the scarcity of high-quality RGB-D datasets. Experimental results demonstrate that a network trained on our low resolution synthetic images generalizes effectively to high resolution (12MP) real-world images across diverse scenes.

Guocheng Qian, Yuanhao Wang, Jinjin Gu et al.

Imaging is usually a mixture problem of incomplete color sampling, noise degradation, and limited resolution. This mixture problem is typically solved by a sequential solution that applies demosaicing (DM), denoising (DN), and super-resolution (SR) sequentially in a fixed and predefined pipeline (execution order of tasks), DM$\to$DN$\to$SR. The most recent work on image processing focuses on developing more sophisticated architectures to achieve higher image quality. Little attention has been paid to the design of the pipeline, and it is still not clear how significant the pipeline is to image quality. In this work, we comprehensively study the effects of pipelines on the mixture problem of learning-based DN, DM, and SR, in both sequential and joint solutions. On the one hand, in sequential solutions, we find that the pipeline has a non-trivial effect on the resulted image quality. Our suggested pipeline DN$\to$SR$\to$DM yields consistently better performance than other sequential pipelines in various experimental settings and benchmarks. On the other hand, in joint solutions, we propose an end-to-end Trinity Pixel Enhancement NETwork (TENet) that achieves state-of-the-art performance for the mixture problem. We further present a novel and simple method that can integrate a certain pipeline into a given end-to-end network by providing intermediate supervision using a detachable head. Extensive experiments show that an end-to-end network with the proposed pipeline can attain only a consistent but insignificant improvement. Our work indicates that the investigation of pipelines is applicable in sequential solutions, but is not very necessary in end-to-end networks. \RR{Code, models, and our contributed PixelShift200 dataset are available at \url{https://github.com/guochengqian/TENet}

Matheus Souza, Wolfgang Heidrich

Image signal processors (ISPs) are historically grown legacy software systems for reconstructing color images from noisy raw sensor measurements. Each smartphone manufacturer has developed its ISPs with its own characteristic heuristics for improving the color rendition, for example, skin tones and other visually essential colors. The recent interest in replacing the historically grown ISP systems with deep-learned pipelines to match DSLR's image quality improves structural features in the image. However, these works ignore the superior color processing based on semantic scene analysis that distinguishes mobile phone ISPs from DSLRs. Here, we present MetaISP, a single model designed to learn how to translate between the color and local contrast characteristics of different devices. MetaISP takes the RAW image from device A as input and translates it to RGB images that inherit the appearance characteristics of devices A, B, and C. We achieve this result by employing a lightweight deep learning technique that conditions its output appearance based on the device of interest. In this approach, we leverage novel attention mechanisms inspired by cross-covariance to learn global scene semantics. Additionally, we use the metadata that typically accompanies RAW images and estimate scene illuminants when they are unavailable.

Haoyu Wei, Xin Liu, Yuhui Liu et al.

End-to-end (E2E) designed imaging systems integrate coded optical designs with decoding algorithms to enhance imaging fidelity for diverse visual tasks. However, existing E2E designs encounter significant challenges in maintaining high image fidelity at wide fields of view, due to high computational complexity, as well as difficulties in modeling off-axis wave propagation while accounting for off-axis aberrations. In particular, the common approach of placing the encoding element into the aperture or pupil plane results in only a global control of the wavefront. To overcome these limitations, this work explores an additional design choice by positioning a DOE off-aperture, enabling a spatial unmixing of the degrees of freedom and providing local control over the wavefront over the image plane. Our approach further leverages hybrid refractive-diffractive optical systems by linking differentiable ray and wave optics modeling, thereby optimizing depth imaging quality and demonstrating system versatility. Experimental results reveal that the off-aperture DOE enhances the imaging quality by over 5 dB in PSNR at a FoV of approximately $45^\circ$ when paired with a simple thin lens, outperforming traditional on-aperture systems. Furthermore, we successfully recover color and depth information at nearly $28^\circ$ FoV using off-aperture DOE configurations with compound optics. Physical prototypes for both applications validate the effectiveness and versatility of the proposed method.

Xinge Yang, Zhaocheng Liu, Zhaoyu Nie et al.

Geometric waveguides are a promising architecture for optical see-through augmented reality displays, but their performance is severely bottlenecked by the difficulty of jointly optimizing non-sequential light transport and polarization-dependent multilayer thin-film coatings. Here we present the first end-to-end differentiable optimization framework for geometric waveguide that couples non-sequential Monte Carlo polarization ray tracing with a differentiable transfer-matrix thin-film solver. A differentiable Monte Carlo ray tracer avoids the exponential growth of deterministic ray splitting while enabling gradients backpropagation from eyebox metrics to design parameters. With memory-saving strategies, we optimize more than one thousand layer-thickness parameters and billions of non-sequential ray-surface intersections on a single multi-GPU workstation. Automated layer pruning is achieved by starting from over-parameterized stacks and driving redundant layers to zero thickness under discrete manufacturability constraints, effectively performing topology optimization to discover optimal coating structures. On a representative design, starting from random initialization within thickness bounds, our method increases light efficiency from 4.1\% to 33.5\% and improves eyebox and FoV uniformity by $\sim$17$\times$ and $\sim$11$\times$, respectively. Furthermore, we jointly optimize the waveguide and an image preprocessing network to improve perceived image quality. Our framework not only enables system-level, high-dimensional coating optimization inside the waveguide, but also expands the scope of differentiable optics for next-generation optical design.

Juan Romero, Qiang Fu, Matteo Ravasi et al.

Hyperspectral image reconstruction from a compressed measurement is a highly ill-posed inverse problem. Current data-driven methods suffer from hallucination due to the lack of spectral diversity in existing hyperspectral image datasets, particularly when they are evaluated for the metamerism phenomenon. In this work, we formulate hyperspectral image (HSI) reconstruction as a Bayesian inference problem and propose a framework, HSDiff, that utilizes an unconditionally trained, pixel-level diffusion prior and posterior diffusion sampling to generate diverse HSI samples consistent with the measurements of various hyperspectral image formation models. We propose an enhanced metameric augmentation technique using region-based metameric black and partition-of-union spectral upsampling to expand training with physically valid metameric spectra, strengthening the prior diversity and improving uncertainty calibration. We utilize HSDiff to investigate how the studied forward models shape the posterior distribution and demonstrate that guiding with effective spectral encoding provides calibrated informative uncertainty compared to non-encoded models. Through the lens of the Bayesian framework, HSDiff offers a complete, high-performance method for uncertainty-aware HSI reconstruction. Our results also reiterate the significance of effective spectral encoding in snapshot hyperspectral imaging.

Piyush Dashpute, Niki Nezakati, Wolfgang Heidrich et al.

Thermal images from low-cost cameras often suffer from low resolution, fixed pattern noise, and other localized degradations. Available datasets for thermal imaging are also limited in both size and diversity. To address these challenges, we propose a patch-based diffusion framework (TDiff) that leverages the local nature of these distortions by training on small thermal patches. In this approach, full-resolution images are restored by denoising overlapping patches and blending them using smooth spatial windowing. To our knowledge, this is the first patch-based diffusion framework that models a learned prior for thermal image restoration across multiple tasks. Experiments on denoising, super-resolution, and deblurring demonstrate strong results on both simulated and real thermal data, establishing our method as a unified restoration pipeline.

Kaixuan Wei, Hector A. Jimenez-Romero, Hadi Amata et al.

Differentiable optics, as an emerging paradigm that jointly optimizes optics and (optional) image processing algorithms, has made innovative optical designs possible across a broad range of applications. Many of these systems utilize diffractive optical components (DOEs) for holography, PSF engineering, or wavefront shaping. Existing approaches have, however, mostly remained limited to laboratory prototypes, owing to a large quality gap between simulation and manufactured devices. We aim at lifting the fundamental technical barriers to the practical use of learned diffractive optical systems. To this end, we propose a fabrication-aware design pipeline for diffractive optics fabricated by direct-write grayscale lithography followed by nano-imprinting replication, which is directly suited for inexpensive mass production of large area designs. We propose a super-resolved neural lithography model that can accurately predict the 3D geometry generated by the fabrication process. This model can be seamlessly integrated into existing differentiable optics frameworks, enabling fabrication-aware, end-to-end optimization of computational optical systems. To tackle the computational challenges, we also devise tensor-parallel compute framework centered on distributing large-scale FFT computation across many GPUs. As such, we demonstrate large scale diffractive optics designs up to 32.16 mm $\times$ 21.44 mm, simulated on grids of up to 128,640 by 85,760 feature points. We find adequate agreement between simulation and fabricated prototypes for applications such as holography and PSF engineering. We also achieve high image quality from an imaging system comprised only of a single DOE, with images processed only by a Wiener filter utilizing the simulation PSF. We believe our findings lift the fabrication limitations for real-world applications of diffractive optics and differentiable optical design.

Shi Mao, Yogeshwar Nath Mishra, Wolfgang Heidrich

The desire for cameras with smaller form factors has recently lead to a push for exploring computational imaging systems with reduced optical complexity such as a smaller number of lens elements. Unfortunately such simplified optical systems usually suffer from severe aberrations, especially in off-axis regions, which can be difficult to correct purely in software. In this paper we introduce Fovea Stacking , a new type of imaging system that utilizes emerging dynamic optical components called deformable phase plates (DPPs) for localized aberration correction anywhere on the image sensor. By optimizing DPP deformations through a differentiable optical model, off-axis aberrations are corrected locally, producing a foveated image with enhanced sharpness at the fixation point - analogous to the eye's fovea. Stacking multiple such foveated images, each with a different fixation point, yields a composite image free from aberrations. To efficiently cover the entire field of view, we propose joint optimization of DPP deformations under imaging budget constraints. Due to the DPP device's non-linear behavior, we introduce a neural network-based control model for improved alignment between simulation-hardware performance. We further demonstrated that for extended depth-of-field imaging, fovea stacking outperforms traditional focus stacking in image quality. By integrating object detection or eye-tracking, the system can dynamically adjust the lens to track the object of interest-enabling real-time foveated video suitable for downstream applications such as surveillance or foveated virtual reality displays

Akshat Dave, Tianyi Zhang, Aaron Young et al.

Photoelasticity enables full-field stress analysis in transparent objects through stress-induced birefringence. Existing techniques are limited to 2D slices and require destructively slicing the object. Recovering the internal 3D stress distribution of the entire object is challenging as it involves solving a tensor tomography problem and handling phase wrapping ambiguities. We introduce NeST, an analysis-by-synthesis approach for reconstructing 3D stress tensor fields as neural implicit representations from polarization measurements. Our key insight is to jointly handle phase unwrapping and tensor tomography using a differentiable forward model based on Jones calculus. Our non-linear model faithfully matches real captures, unlike prior linear approximations. We develop an experimental multi-axis polariscope setup to capture 3D photoelasticity and experimentally demonstrate that NeST reconstructs the internal stress distribution for objects with varying shape and force conditions. Additionally, we showcase novel applications in stress analysis, such as visualizing photoelastic fringes by virtually slicing the object and viewing photoelastic fringes from unseen viewpoints. NeST paves the way for scalable non-destructive 3D photoelastic analysis.

Miao Qi, Ramzi Idoughi, Wolfgang Heidrich

Flow estimation problems are ubiquitous in scientific imaging. Often, the underlying flows are subject to physical constraints that can be exploited in the flow estimation; for example, incompressible (divergence-free) flows are expected for many fluid experiments, while irrotational (curl-free) flows arise in the analysis of optical distortions and wavefront sensing. In this work, we propose a Physics- Inspired Neural Network (PINN) named HDNet, which performs a Helmholtz decomposition of an arbitrary flow field, i.e., it decomposes the input flow into a divergence-only and a curl-only component. HDNet can be trained exclusively on synthetic data generated by reverse Helmholtz decomposition, which we call Helmholtz synthesis. As a PINN, HDNet is fully differentiable and can easily be integrated into arbitrary flow estimation problems.

Xinge Yang, Matheus Souza, Kunyi Wang et al.

Hybrid refractive-diffractive lenses combine the light efficiency of refractive lenses with the information encoding power of diffractive optical elements (DOE), showing great potential as the next generation of imaging systems. However, accurately simulating such hybrid designs is generally difficult, and in particular, there are no existing differentiable image formation models for hybrid lenses with sufficient accuracy. In this work, we propose a new hybrid ray-tracing and wave-propagation (ray-wave) model for accurate simulation of both optical aberrations and diffractive phase modulation, where the DOE is placed between the last refractive surface and the image sensor, i.e. away from the Fourier plane that is often used as a DOE position. The proposed ray-wave model is fully differentiable, enabling gradient back-propagation for end-to-end co-design of refractive-diffractive lens optimization and the image reconstruction network. We validate the accuracy of the proposed model by comparing the simulated point spread functions (PSFs) with theoretical results, as well as simulation experiments that show our model to be more accurate than solutions implemented in commercial software packages like Zemax. We demonstrate the effectiveness of the proposed model through real-world experiments and show significant improvements in both aberration correction and extended depth-of-field (EDoF) imaging. We believe the proposed model will motivate further investigation into a wide range of applications in computational imaging, computational photography, and advanced optical design. Code will be released upon publication.

Juan Romero, Wolfgang Heidrich, Nick Luiken et al.

Seismic imaging is the numerical process of creating a volumetric representation of the subsurface geological structures from elastic waves recorded at the surface of the Earth. As such, it is widely utilized in the energy and construction sectors for applications ranging from oil and gas prospection, to geothermal production and carbon capture and storage monitoring, to geotechnical assessment of infrastructures. Extracting quantitative information from seismic recordings, such as an acoustic impedance model, is however a highly ill-posed inverse problem, due to the band-limited and noisy nature of the data. This paper introduces IntraSeismic, a novel hybrid seismic inversion method that seamlessly combines coordinate-based learning with the physics of the post-stack modeling operator. Key features of IntraSeismic are i) unparalleled performance in 2D and 3D post-stack seismic inversion, ii) rapid convergence rates, iii) ability to seamlessly include hard constraints (i.e., well data) and perform uncertainty quantification, and iv) potential data compression and fast randomized access to portions of the inverted model. Synthetic and field data applications of IntraSeismic are presented to validate the effectiveness of the proposed method.

Xinge Yang, Qiang Fu, Yunfeng Nie et al.

Classical lens design minimizes optical aberrations to produce sharp images, but is typically decoupled from downstream computer vision tasks. Existing end-to-end optical design learns optical encoding through joint optimization, but often suffers from an unstable training process. We propose task-driven lens design, a new optimization philosophy for joint optics-network systems. We freeze the pretrained vision model and optimize only the lens so that the image formation better fits the model's feature preferences. This network-frozen setting yields a low-dimensional and stable optimization process, enabling lens design from scratch without human intervention, thereby exploring a broader design space. Multiple computer vision experiments show that TaskLenses outperform classical ImagingLenses with the same or even fewer elements. Our analysis reveals that the learned optics exhibit long-tailed point spread functions, better preserving preferred structural cues when aberrations cannot be fully corrected. These results highlight task-driven design as a practical route for optical lenses that are compatible with modern vision models, and also inspire new optical design objectives beyond traditional aberration minimization.

Rui Li, Darius Rückert, Yuanhao Wang et al.

Neural rendering with implicit neural networks has recently emerged as an attractive proposition for scene reconstruction, achieving excellent quality albeit at high computational cost. While the most recent generation of such methods has made progress on the rendering (inference) times, very little progress has been made on improving the reconstruction (training) times. In this work, we present Neural Adaptive Scene Tracing (NAScenT), the first neural rendering method based on directly training a hybrid explicit-implicit neural representation. NAScenT uses a hierarchical octree representation with one neural network per leaf node and combines this representation with a two-stage sampling process that concentrates ray samples where they matter most near object surfaces. As a result, NAScenT is capable of reconstructing challenging scenes including both large, sparsely populated volumes like UAV captured outdoor environments, as well as small scenes with high geometric complexity. NAScenT outperforms existing neural rendering approaches in terms of both quality and training time.

Darius Rückert, Yuanhao Wang, Rui Li et al.

In this paper, we present Neural Adaptive Tomography (NeAT), the first adaptive, hierarchical neural rendering pipeline for multi-view inverse rendering. Through a combination of neural features with an adaptive explicit representation, we achieve reconstruction times far superior to existing neural inverse rendering methods. The adaptive explicit representation improves efficiency by facilitating empty space culling and concentrating samples in complex regions, while the neural features act as a neural regularizer for the 3D reconstruction. The NeAT framework is designed specifically for the tomographic setting, which consists only of semi-transparent volumetric scenes instead of opaque objects. In this setting, NeAT outperforms the quality of existing optimization-based tomography solvers while being substantially faster.

Masheal Alghamdi, Qiang Fu, Ali Thabet et al.

This paper study the reconstruction of High Dynamic Range (HDR) video from snapshot-coded LDR video. Constructing an HDR video requires restoring the HDR values for each frame and maintaining the consistency between successive frames. HDR image acquisition from single image capture, also known as snapshot HDR imaging, can be achieved in several ways. For example, the reconfigurable snapshot HDR camera is realized by introducing an optical element into the optical stack of the camera; by placing a coded mask at a small standoff distance in front of the sensor. High-quality HDR image can be recovered from the captured coded image using deep learning methods. This study utilizes 3D-CNNs to perform a joint demosaicking, denoising, and HDR video reconstruction from coded LDR video. We enforce more temporally consistent HDR video reconstruction by introducing a temporal loss function that considers the short-term and long-term consistency. The obtained results are promising and could lead to affordable HDR video capture using conventional cameras.

Miao Qi, Yuqi Li, Wolfgang Heidrich

Under-display cameras have been proposed in recent years as a way to reduce the form factor of mobile devices while maximizing the screen area. Unfortunately, placing the camera behind the screen results in significant image distortions, including loss of contrast, blur, noise, color shift, scattering artifacts, and reduced light sensitivity. In this paper, we propose an image-restoration pipeline that is ISP-agnostic, i.e. it can be combined with any legacy ISP to produce a final image that matches the appearance of regular cameras using the same ISP. This is achieved with a deep learning approach that performs a RAW-to-RAW image restoration. To obtain large quantities of real under-display camera training data with sufficient contrast and scene diversity, we furthermore develop a data capture method utilizing an HDR monitor, as well as a data augmentation method to generate suitable HDR content. The monitor data is supplemented with real-world data that has less scene diversity but allows us to achieve fine detail recovery without being limited by the monitor resolution. Together, this approach successfully restores color and contrast as well as image detail.

Rui Li, Guangmin Zang, Miao Qi et al.

Simultaneous reconstruction of geometry and reflectance properties in uncontrolled environments remains a challenging problem. In this paper, we propose an efficient method to reconstruct the scene's 3D geometry and reflectance from multi-view photography using conventional hand-held cameras. Our method automatically builds a virtual scene in a differentiable rendering system that roughly matches the real world's scene parameters, optimized by minimizing photometric objectives alternatingly and stochastically. With the optimal scene parameters evaluated, photo-realistic novel views for various viewing angles and distances can then be generated by our approach. We present the results of captured scenes with complex geometry and various reflection types. Our method also shows superior performance compared to state-of-the-art alternatives in novel view synthesis visually and quantitatively.

Qiang Fu, Dong-Ming Yan, Wolfgang Heidrich

Lensless cameras are a class of imaging devices that shrink the physical dimensions to the very close vicinity of the image sensor by replacing conventional compound lenses with integrated flat optics and computational algorithms. Here we report a diffractive lensless camera with spatially-coded Voronoi-Fresnel phase to achieve superior image quality. We propose a design principle of maximizing the acquired information in optics to facilitate the computational reconstruction. By introducing an easy-to-optimize Fourier domain metric, Modulation Transfer Function volume (MTFv), which is related to the Strehl ratio, we devise an optimization framework to guide the optimization of the diffractive optical element. The resulting Voronoi-Fresnel phase features an irregular array of quasi-Centroidal Voronoi cells containing a base first-order Fresnel phase function. We demonstrate and verify the imaging performance for photography applications with a prototype Voronoi-Fresnel lensless camera on a 1.6-megapixel image sensor in various illumination conditions. Results show that the proposed design outperforms existing lensless cameras, and could benefit the development of compact imaging systems that work in extreme physical conditions.

Ethan Tseng, Grace Kuo, Seung-Hwan Baek et al.

Holographic displays can generate light fields by dynamically modulating the wavefront of a coherent beam of light using a spatial light modulator, promising rich virtual and augmented reality applications. However, the limited spatial resolution of existing dynamic spatial light modulators imposes a tight bound on the diffraction angle. As a result, modern holographic displays possess low étendue, which is the product of the display area and the maximum solid angle of diffracted light. The low étendue forces a sacrifice of either the field-of-view (FOV) or the display size. In this work, we lift this limitation by presenting neural étendue expanders. This new breed of optical elements, which is learned from a natural image dataset, enables higher diffraction angles for ultra-wide FOV while maintaining both a compact form factor and the fidelity of displayed contents to human viewers. With neural étendue expanders, we experimentally achieve 64$\times$ étendue expansion of natural images in full color, expanding the FOV by an order of magnitude horizontally and vertically, with high-fidelity reconstruction quality (measured in PSNR) over 29 dB on retinal-resolution images.

Ilya Chugunov, Seung-Hwan Baek, Qiang Fu et al.

We introduce Mask-ToF, a method to reduce flying pixels (FP) in time-of-flight (ToF) depth captures. FPs are pervasive artifacts which occur around depth edges, where light paths from both an object and its background are integrated over the aperture. This light mixes at a sensor pixel to produce erroneous depth estimates, which can adversely affect downstream 3D vision tasks. Mask-ToF starts at the source of these FPs, learning a microlens-level occlusion mask which effectively creates a custom-shaped sub-aperture for each sensor pixel. This modulates the selection of foreground and background light mixtures on a per-pixel basis and thereby encodes scene geometric information directly into the ToF measurements. We develop a differentiable ToF simulator to jointly train a convolutional neural network to decode this information and produce high-fidelity, low-FP depth reconstructions. We test the effectiveness of Mask-ToF on a simulated light field dataset and validate the method with an experimental prototype. To this end, we manufacture the learned amplitude mask and design an optical relay system to virtually place it on a high-resolution ToF sensor. We find that Mask-ToF generalizes well to real data without retraining, cutting FP counts in half.

Seung-Hwan Baek, Hayato Ikoma, Daniel S. Jeon et al.

Imaging depth and spectrum have been extensively studied in isolation from each other for decades. Recently, hyperspectral-depth (HS-D) imaging emerges to capture both information simultaneously by combining two different imaging systems; one for depth, the other for spectrum. While being accurate, this combinational approach induces increased form factor, cost, capture time, and alignment/registration problems. In this work, departing from the combinational principle, we propose a compact single-shot monocular HS-D imaging method. Our method uses a diffractive optical element (DOE), the point spread function of which changes with respect to both depth and spectrum. This enables us to reconstruct spectrum and depth from a single captured image. To this end, we develop a differentiable simulator and a neural-network-based reconstruction that are jointly optimized via automatic differentiation. To facilitate learning the DOE, we present a first HS-D dataset by building a benchtop HS-D imager that acquires high-quality ground truth. We evaluate our method with synthetic and real experiments by building an experimental prototype and achieve state-of-the-art HS-D imaging results.

Jinhui Xiong, Peter Richtárik, Wolfgang Heidrich

State-of-the-art methods for Convolutional Sparse Coding usually employ Fourier-domain solvers in order to speed up the convolution operators. However, this approach is not without shortcomings. For example, Fourier-domain representations implicitly assume circular boundary conditions and make it hard to fully exploit the sparsity of the problem as well as the small spatial support of the filters. In this work, we propose a novel stochastic spatial-domain solver, in which a randomized subsampling strategy is introduced during the learning sparse codes. Afterwards, we extend the proposed strategy in conjunction with online learning, scaling the CSC model up to very large sample sizes. In both cases, we show experimentally that the proposed subsampling strategy, with a reasonable selection of the subsampling rate, outperforms the state-of-the-art frequency-domain solvers in terms of execution time without losing the learning quality. Finally, we evaluate the effectiveness of the over-complete dictionary learned from large-scale datasets, which demonstrates an improved sparse representation of the natural images on account of more abundant learned image features.

Marie-Lena Eckert, Wolfgang Heidrich, Nils Thuerey

We present a novel method to reconstruct a fluid's 3D density and motion based on just a single sequence of images. This is rendered possible by using powerful physical priors for this strongly under-determined problem. More specifically, we propose a novel strategy to infer density updates strongly coupled to previous and current estimates of the flow motion. Additionally, we employ an accurate discretization and depth-based regularizers to compute stable solutions. Using only one view for the reconstruction reduces the complexity of the capturing setup drastically and could even allow for online video databases or smart-phone videos as inputs. The reconstructed 3D velocity can then be flexibly utilized, e.g., for re-simulation, domain modification or guiding purposes. We will demonstrate the capacity of our method with a series of synthetic test cases and the reconstruction of real smoke plumes captured with a Raspberry Pi camera.

Ibrahim Alsolami, Wolfgang Heidrich

This paper addresses the problem of imaging in the presence of diffraction-photons. Diffraction-photons arise from the low contrast ratio of DMDs ($\sim\,1000:1$), and very much degrade the quality of images captured by SPAD-based systems. Herein, a joint illumination-deconvolution scheme is designed to overcome diffraction-photons, enabling the acquisition of intensity and depth images. Additionally, a proof-of-concept experiment is conducted to demonstrate the viability of the designed scheme. It is shown that by co-designing the illumination and deconvolution phases of imaging, one can substantially overcome diffraction-photons.

Lei Xiao, Felix Heide, Wolfgang Heidrich et al.

Recently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency. However, these methods require separate training for each restoration task (e.g., denoising, deblurring, demosaicing) and problem condition (e.g., noise level of input images). This makes it time-consuming and difficult to encompass all tasks and conditions during training. In this paper, we propose a discriminative transfer learning method that incorporates formal proximal optimization and discriminative learning for general image restoration. The method requires a single-pass training and allows for reuse across various problems and conditions while achieving an efficiency comparable to previous discriminative approaches. Furthermore, after being trained, our model can be easily transferred to new likelihood terms to solve untrained tasks, or be combined with existing priors to further improve image restoration quality.

Shuochen Su, Mauricio Delbracio, Jue Wang et al.

Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on aligning nearby frames. However, aligning images is a computationally expensive and fragile procedure, and methods that aggregate information must therefore be able to identify which regions have been accurately aligned and which have not, a task which requires high level scene understanding. In this work, we introduce a deep learning solution to video deblurring, where a CNN is trained end-to-end to learn how to accumulate information across frames. To train this network, we collected a dataset of real videos recorded with a high framerate camera, which we use to generate synthetic motion blur for supervision. We show that the features learned from this dataset extend to deblurring motion blur that arises due to camera shake in a wide range of videos, and compare the quality of results to a number of other baselines.

Mohamed Aly, Wolfgang Heidrich

We present a novel algorithm for blind denoising of images corrupted by mixed impulse, Poisson, and Gaussian noises. The algorithm starts by applying the Anscombe variance-stabilizing transformation to convert the Poisson into white Gaussian noise. Then it applies a combinatorial optimization technique to denoise the mixed impulse Gaussian noise using proximal algorithms. The result is then processed by the inverse Anscombe transform. We compare our algorithm to state of the art methods on standard images, and show its superior performance in various noise conditions.

Mohamed Aly, Guangming Zang, Wolfgang Heidrich et al.

We present TRex, a flexible and robust Tomographic Reconstruction framework using proximal algorithms. We provide an overview and perform an experimental comparison between the famous iterative reconstruction methods in terms of reconstruction quality in sparse view situations. We then derive the proximal operators for the four best methods. We show the flexibility of our framework by deriving solvers for two noise models: Gaussian and Poisson; and by plugging in three powerful regularizers. We compare our framework to state of the art methods, and show superior quality on both synthetic and real datasets.