Search

Despite an emerging interest in MIMO radar, the utilization of its complementary strengths in combination with optical sensors has so far been limited to far-field applications, due to the challenges that arise from mutual sensor calibration in the near field. In fact, most related approaches in the autonomous industry propose target-based calibration methods using corner reflectors that have proven to be unsuitable for the near field. In contrast, we propose a novel, joint calibration approach for optical RGB-D sensors and MIMO radars that is designed to operate in the radar's near-field range, within decimeters from the sensors. Our pipeline consists of a bespoke calibration target, allowing for automatic target detection and localization, followed by the spatial calibration of the two sensor coordinate systems through target registration. We validate our approach using two different depth sensing technologies from the optical domain. The experiments show the efficiency and accuracy of our calibration for various target displacements, as well as its robustness of our localization in terms of signal ambiguities., Comment: 8 pages, 9 figures

Anomaly detection and localization in images is a growing field in computer vision. In this area, a seemingly understudied problem is anomaly clustering, i.e., identifying and grouping different types of anomalies in a fully unsupervised manner. In this work, we propose a novel method for clustering anomalies in largely stationary images (textures) in a blind setting. That is, the input consists of normal and anomalous images without distinction and without labels. What contributes to the difficulty of the task is that anomalous regions are often small and may present only subtle changes in appearance, which can be easily overshadowed by the genuine variance in the texture. Moreover, each anomaly type may have a complex appearance distribution. We introduce a novel scheme for solving this task using a combination of blind anomaly localization and contrastive learning. By identifying the anomalous regions with high fidelity, we can restrict our focus to those regions of interest; then, contrastive learning is employed to increase the separability of different anomaly types and reduce the intra-class variation. Our experiments show that the proposed solution yields significantly better results compared to prior work, setting a new state of the art. Project page: https://reality.tf.fau.de/pub/ardelean2024blind.html.

Portrait viewpoint and illumination editing is an important problem with several applications in VR/AR, movies, and photography. Comprehensive knowledge of geometry and illumination is critical for obtaining photorealistic results. Current methods are unable to explicitly model in 3D while handling both viewpoint and illumination editing from a single image. In this paper, we propose VoRF, a novel approach that can take even a single portrait image as input and relight human heads under novel illuminations that can be viewed from arbitrary viewpoints. VoRF represents a human head as a continuous volumetric field and learns a prior model of human heads using a coordinate-based MLP with individual latent spaces for identity and illumination. The prior model is learned in an auto-decoder manner over a diverse class of head shapes and appearances, allowing VoRF to generalize to novel test identities from a single input image. Additionally, VoRF has a reflectance MLP that uses the intermediate features of the prior model for rendering One-Light-at-A-Time (OLAT) images under novel views. We synthesize novel illuminations by combining these OLAT images with target environment maps. Qualitative and quantitative evaluations demonstrate the effectiveness of VoRF for relighting and novel view synthesis, even when applied to unseen subjects under uncontrolled illumination. This work is an extension of Rao et al. (VoRF: Volumetric Relightable Faces 2022). We provide extensive evaluation and ablative studies of our model and also provide an application, where any face can be relighted using textual input.

We propose a novel method for Zero-Shot Anomaly Localization on textures. The task refers to identifying abnormal regions in an otherwise homogeneous image. To obtain a high-fidelity localization, we leverage a bijective mapping derived from the 1-dimensional Wasserstein Distance. As opposed to using holistic distances between distributions, the proposed approach allows pinpointing the non-conformity of a pixel in a local context with increased precision. By aggregating the contribution of the pixel to the errors of all nearby patches we obtain a reliable anomaly score estimate. We validate our solution on several datasets and obtain more than a 40% reduction in error over the previous state of the art on the MVTec AD dataset in a zero-shot setting. Also see https://reality.tf.fau.de/pub/ardelean2024highfidelity.html.

Photorealistic editing of head portraits is a challenging task as humans are very sensitive to inconsistencies in faces. We present an approach for high-quality intuitive editing of the camera viewpoint and scene illumination (parameterised with an environment map) in a portrait image. This requires our method to capture and control the full reflectance field of the person in the image. Most editing approaches rely on supervised learning using training data captured with setups such as light and camera stages. Such datasets are expensive to acquire, not readily available and do not capture all the rich variations of in-the-wild portrait images. In addition, most supervised approaches only focus on relighting, and do not allow camera viewpoint editing. Thus, they only capture and control a subset of the reflectance field. Recently, portrait editing has been demonstrated by operating in the generative model space of StyleGAN. While such approaches do not require direct supervision, there is a significant loss of quality when compared to the supervised approaches. In this paper, we present a method which learns from limited supervised training data. The training images only include people in a fixed neutral expression with eyes closed, without much hair or background variations. Each person is captured under 150 one-light-at-a-time conditions and under 8 camera poses. Instead of training directly in the image space, we design a supervised problem which learns transformations in the latent space of StyleGAN. This combines the best of supervised learning and generative adversarial modeling. We show that the StyleGAN prior allows for generalisation to different expressions, hairstyles and backgrounds. This produces high-quality photorealistic results for in-the-wild images and significantly outperforms existing methods. Our approach can edit the illumination and pose simultaneously, and runs at interactive rates.

Computer-Generated Holography (CGH) offers the potential for genuine, high-quality three-dimensional visuals. However, fulfilling this potential remains a practical challenge due to computational complexity and visual quality issues. We propose a new CGH method that exploits gaze-contingency and perceptual graphics to accelerate the development of practical holographic display systems. Firstly, our method infers the user's focal depth and generates images only at their focus plane without using any moving parts. Second, the images displayed are metamers; in the user's peripheral vision, they need only be statistically correct and blend with the fovea seamlessly. Unlike previous methods, our method prioritises and improves foveal visual quality without causing perceptually visible distortions at the periphery. To enable our method, we introduce a novel metameric loss function that robustly compares the statistics of two given images for a known gaze location. In parallel, we implement a model representing the relation between holograms and their image reconstructions. We couple our differentiable loss function and model to metameric varifocal holograms using a stochastic gradient descent solver. We evaluate our method with an actual proof-of-concept holographic display, and we show that our CGH method leads to practical and perceptually three-dimensional image reconstructions.

Photorealistic editing of head portraits is a challenging task as humans are very sensitive to inconsistencies in faces. We present an approach for high-quality intuitive editing of the camera viewpoint and scene illumination (parameterised with an environment map) in a portrait image. This requires our method to capture and control the full reflectance field of the person in the image. Most editing approaches rely on supervised learning using training data captured with setups such as light and camera stages. Such datasets are expensive to acquire, not readily available and do not capture all the rich variations of in-the-wild portrait images. In addition, most supervised approaches only focus on relighting, and do not allow camera viewpoint editing. Thus, they only capture and control a subset of the reflectance field. Recently, portrait editing has been demonstrated by operating in the generative model space of StyleGAN. While such approaches do not require direct supervision, there is a significant loss of quality when compared to the supervised approaches. In this paper, we present a method which learns from limited supervised training data. The training images only include people in a fixed neutral expression with eyes closed, without much hair or background variations. Each person is captured under 150 one-light-at-a-time conditions and under 8 camera poses. Instead of training directly in the image space, we design a supervised problem which learns transformations in the latent space of StyleGAN. This combines the best of supervised learning and generative adversarial modeling. We show that the StyleGAN prior allows for generalisation to different expressions, hairstyles and backgrounds. This produces high-quality photorealistic results for in-the-wild images and significantly outperforms existing methods. Our approach can edit the illumination and pose simultaneously, and runs at interactive rates.

Photorealistic editing of portraits is a challenging task as humans are very sensitive to inconsistencies in faces. We present an approach for high-quality intuitive editing of the camera viewpoint and scene illumination in a portrait image. This requires our method to capture and control the full reflectance field of the person in the image. Most editing approaches rely on supervised learning using training data captured with setups such as light and camera stages. Such datasets are expensive to acquire, not readily available and do not capture all the rich variations of in-the-wild portrait images. In addition, most supervised approaches only focus on relighting, and do not allow camera viewpoint editing. Thus, they only capture and control a subset of the reflectance field. Recently, portrait editing has been demonstrated by operating in the generative model space of StyleGAN. While such approaches do not require direct supervision, there is a significant loss of quality when compared to the supervised approaches. In this paper, we present a method which learns from limited supervised training data. The training images only include people in a fixed neutral expression with eyes closed, without much hair or background variations. Each person is captured under 150 one-light-at-a-time conditions and under 8 camera poses. Instead of training directly in the image space, we design a supervised problem which learns transformations in the latent space of StyleGAN. This combines the best of supervised learning and generative adversarial modeling. We show that the StyleGAN prior allows for generalisation to different expressions, hairstyles and backgrounds. This produces high-quality photorealistic results for in-the-wild images and significantly outperforms existing methods. Our approach can edit the illumination and pose simultaneously, and runs at interactive rates., Comment: http://gvv.mpi-inf.mpg.de/projects/PhotoApp

Controlled capture of real-world material appearance yields tabulated sets of highly realistic reflectance data. In practice, however, its high memory footprint requires compressing into a representation that can be used efficiently in rendering while remaining faithful to the original. Previous works in appearance encoding often prioritised one of these requirements at the expense of the other, by either applying high-fidelity array compression strategies not suited for efficient queries during rendering, or by fitting a compact analytic model that lacks expressiveness. We present a compact neural network-based representation of BRDF data that combines high-accuracy reconstruction with efficient practical rendering via built-in interpolation of reflectance. We encode BRDFs as lightweight networks, and propose a training scheme with adaptive angular sampling, critical for the accurate reconstruction of specular highlights. Additionally, we propose a novel approach to make our representation amenable to importance sampling: rather than inverting the trained networks, we learn to encode them in a more compact embedding that can be mapped to parameters of an analytic BRDF for which importance sampling is known. We evaluate encoding results on isotropic and anisotropic BRDFs from multiple real-world datasets, and importance sampling performance for isotropic BRDFs mapped to two different analytic models.

Fast methods for convolution and correlation underlie a variety of applications in computer vision and graphics, including efficient filtering, analysis, and simulation. However, standard convolution and correlation are inherently limited to fixed filters: spatial adaptation is impossible without sacrificing efficient computation. In early work, Freeman and Adelson have shown how steerable filters can address this limitation, providing a way for rotating the filter as it is passed over the signal. In this work, we provide a general, representation-theoretic, framework that allows for spatially varying linear transformations to be applied to the filter. This framework allows for efficient implementation of extended convolution and correlation for transformation groups such as rotation (in 2D and 3D) and scale, and provides a new interpretation for previous methods including steerable filters and the generalized Hough transform. We present applications to pattern matching, image feature description, vector field visualization, and adaptive image filtering.

The reflectance field of a face describes the reflectance properties responsible for complex lighting effects including diffuse, specular, inter-reflection and self shadowing. Most existing methods for estimating the face reflectance from a monocular image assume faces to be diffuse with very few approaches adding a specular component. This still leaves out important perceptual aspects of reflectance as higher-order global illumination effects and self-shadowing are not modeled. We present a new neural representation for face reflectance where we can estimate all components of the reflectance responsible for the final appearance from a single monocular image. Instead of modeling each component of the reflectance separately using parametric models, our neural representation allows us to generate a basis set of faces in a geometric deformation-invariant space, parameterized by the input light direction, viewpoint and face geometry. We learn to reconstruct this reflectance field of a face just from a monocular image, which can be used to render the face from any viewpoint in any light condition. Our method is trained on a light-stage training dataset, which captures 300 people illuminated with 150 light conditions from 8 viewpoints. We show that our method outperforms existing monocular reflectance reconstruction methods, in terms of photorealism due to better capturing of physical premitives, such as sub-surface scattering, specularities, self-shadows and other higher-order effects., Comment: Project page - http://gvv.mpi-inf.mpg.de/projects/FaceReflectanceFields

This paper presents a novel technique for progressive online integration of uncalibrated image sequences with substantial geometric and/or photometric discrepancies into a single, geometrically and photometrically consistent image. Our approach can handle large sets of images, acquired from a nearly planar or infinitely distant scene at different resolutions in object domain and under variable local or global illumination conditions. It allows for efficient user guidance as its progressive nature provides a valid and consistent reconstruction at any moment during the online refinement process. Our approach avoids global optimization techniques, as commonly used in the field of image refinement, and progressively incorporates new imagery into a dynamically extendable and memory-efficient Laplacian pyramid. Our image registration process includes a coarse homography and a local refinement stage using optical flow. Photometric consistency is achieved by retaining the photometric intensities given in a reference image, while it is being refined. Globally blurred imagery and local geometric inconsistencies due to, e.g. motion are detected and removed prior to image fusion. We demonstrate the quality and robustness of our approach using several image and video sequences, including handheld acquisition with mobile phones and zooming sequences with consumer cameras., Comment: This article has been published in final form at https://doi.org/10.1111/cgf.13808

BRDF models are ubiquitous tools for the representation of material appearance. However, there is now an astonishingly large number of different models in practical use. Both a lack of BRDF model standardisation across implementations found in different renderers, as well as the often semantically different capabilities of various models, have grown to be a major hindrance to the interchange of production assets between different rendering systems. Current attempts to solve this problem rely on manually finding visual similarities between models, or mathematical ones between their functional shapes, which requires access to the shader implementation, usually unavailable in commercial renderers. We present a method for automatic translation of material appearance between different BRDF models, which uses an image-based metric for appearance comparison, and that delegates the interaction with the model to the renderer. We analyse the performance of the method, both with respect to robustness and visual differences of the fits for multiple combinations of BRDF models. While it is effective for individual BRDFs, the computational cost does not scale well for spatially-varying BRDFs. Therefore, we further present a parametric regression scheme that approximates the shape of the transformation function and generates a reduced representation which evaluates instantly and without further interaction with the renderer. We present respective visual comparisons of the remapped SVBRDF models for commonly used renderers and shading models, and show that our approach is able to extrapolate transformed BRDF parameters better than other complex regression schemes.

Convolutional neural networks (CNNs) handle the case where filters extend beyond the image boundary using several heuristics, such as zero, repeat or mean padding. These schemes are applied in an ad-hoc fashion and, being weakly related to the image content and oblivious of the target task, result in low output quality at the boundary. In this paper, we propose a simple and effective improvement that learns the boundary handling itself. At training-time, the network is provided with a separate set of explicit boundary filters. At testing-time, we use these filters which have learned to extrapolate features at the boundary in an optimal way for the specific task. Our extensive evaluation, over a wide range of architectural changes (variations of layers, feature channels, or both), shows how the explicit filters result in improved boundary handling. Consequently, we demonstrate an improvement of 5% to 20% across the board of typical CNN applications (colorization, de-Bayering, optical flow, and disparity estimation).

Photographers routinely compose multiple manipulated photos of the same scene (layers) into a single image, which is better than any individual photo could be alone. Similarly, 3D artists set up rendering systems to produce layered images to contain only individual aspects of the light transport, which are composed into the final result in post-production. Regrettably, both approaches either take considerable time to capture, or remain limited to synthetic scenes. In this paper, we suggest a system to allow decomposing a single image into a plausible shading decomposition (PSD) that approximates effects such as shadow, diffuse illumination, albedo, and specular shading. This decomposition can then be manipulated in any off-the-shelf image manipulation software and recomposited back. We perform such a decomposition by learning a convolutional neural network trained using synthetic data. We demonstrate the effectiveness of our decomposition on synthetic (i.e., rendered) and real data (i.e., photographs), and use them for common photo manipulation, which are nearly impossible to perform otherwise from single images., Comment: 8 pages, 9 figures