Recent work has shown that diffusion models can serve as powerful neural rendering engines that can be leveraged for inserting virtual objects into images. However, unlike typical physics-based renderers, these neural rendering engines are limited by the lack of manual control over the lighting, which is often essential for improving or personalizing the desired image outcome. In this paper, we show that precise and controllable lighting can be achieved without any additional training, simply by supplying a coarse shadow hint for the object. Indeed, we show that injecting only the desired shadow of the object into a pre-trained diffusionbased neural renderer enables it to accurately shade the object according to the desired light position, while properly harmonizing the object (and its shadow) within the target background image. Our method, SpotLight, is entirely training-free and leverages existing neural rendering approaches to achieve controllable relighting. We show that SpotLight achieves superior object compositing results, both quantitatively and perceptually, as confirmed by a user study, outperforming existing diffusion-based models specifically designed for relighting. We also demonstrate other applications, such as hand-scribbling shadows and full-image relighting, demonstrating its versatility.

Due to their increased field of view, wide-angle lenses are increasingly used in applications such as VR, security, or in autonomous driving. Typically, existing models either ignore wide-angle distortions or "undistort" images to a perspective projection, often resulting in severe stretching. More recent distortion-aware architectures address these issues, yet they impose substantial computational burdens and limit the use of powerful pre-trained vision backbones. In this work, we revisit the undistortion strategy by exploring alternative projection functions beyond the conventional perspective model. Specifically, we investigate square-to-disc mapping functions, most notably, the elliptical grid map (EGM) projection, which minimizes stretching. We show how EGM projection can be combined with the known lens distortion curves to achieve distortion invariance directly in image space. This network-agnostic approach seamlessly integrates with existing deep learning architectures, allowing fine-tuning on pre-trained models trained on large perspective datasets, while adapting to both seen and unseen wide-angle lenses without re-training each time the lens changes during evaluation. We perform experiments on the semantic segmentation task, comparing methods on zero-shot adaptation to unseen lenses from different wide-angle lenses. Our extensive experiments show that using the EGM projection with existing segmentation models significantly outperforms baselines when trained on bounded distortion levels and tested across both seen and out-of-distribution distortions. Furthermore, EGM projection achieves improved performance on real-world datasets, highlighting the robustness and practicality of our approach in real-world applications. The code and models are publicly available at https://lvsn.github.io/NADA/.

Radiance fields such as 3D Gaussian Splatting allow real-time rendering of scenes captured from photos. They also reconstruct most specular reflections with high visual quality, but typically model them with “fake” reflected geometry, using primitives behind the reflector. Our goal is to correctly reconstruct the reflector and the reflected objects such as to make specular reflections editable; we present a proof of concept which exploits promising learning-based methods to extract diffuse and specular buffers from photos, as well as geometry and BRDF buffers. Our method builds on three key components. First, by using diffuse/specular buffers of input training views, we optimize a diffuse version of the scene and use path tracing to efficiently generate physically-based specular reflections. Second, we present a specialized training method that allows this process to converge. Finally, we present a fast ray tracing algorithm for 3D Gaussian primitives that enables efficient multi-bounce reflections. Our method reconstructs reflectors and reflected objects—including those not seen in the input images—in a unique scene representation. Our solution allows real-time, consistent editing of captured scenes with specular reflections, including multi-bounce effects, changing roughness etc. We mainly show results using ground truth buffers from synthetic scenes, and also preliminary results in real scenes with currently imperfect learning-based buffers. Code and data are available at: https://repo-sam.inria.fr/nerphys/editable-gaussian-reflections/.

Wide angle fisheye images are becoming increasingly common for perception tasks in applications such as robotics, security, and mobility (e.g. drones, avionics). However, current models often either ignore the distortions in wide angle images or are not suitable to perform pixel-level tasks. In this paper, we present an encoder-decoder model based on a radial transformer architecture that adapts to distortions in wide angle lenses by leveraging the physical character-istics defined by the radial distortion profile. In contrast to the original model, which only performs classification tasks, we introduce a U-Net architecture, DarSwin-Unet, designed for pixel level tasks. Furthermore, we propose a novel strategy that minimizes sparsity when sampling the image for creating its input tokens. Our approach enhances the model capability to handle pixel-level tasks in wide angle fisheye images, making it more effective for real-world applications. Compared to other baselines, DarSwin-Unet achieves the best results across different datasets, with significant gains when trained on bounded levels of distortions (very low, low, medium, and high) and tested on all, including out-of-distribution distortions. We demonstrate its performance on depth estimation and show through extensive experiments that DarSwin-Unet can perform zero-shot adaptation to unseen distortions of different wide angle lenses. The code and models are publicly available at https://lvsn.github.io/darswin-unet/.

We present Zerocomp,an effective zero-shot 3D object compositing approach that does not require paired composite-scene images during training. Our method leverages ControlNet to condition from intrinsic images and combines it with a Stable Diffusion model to utilize its scene priors, together operating as an effective rendering engine. During training, Zerocompuses intrinsic images based on geometry, albedo, and masked shading, all without the need for paired images of scenes with and without compos-ite objects. Once trained, it seamlessly integrates virtual 3D objects into scenes, adjusting shading to create realistic composites. We develop a high-quality evaluation dataset and demonstrate that Zerocompoutperforms methods using explicit lighting estimations and generative techniques in quantitative and human perception benchmarks. Additionally, Zerocompextends to real and outdoor image compositing, even when trained solely on synthetic indoor data, showcasing its effectiveness in image compositing.

Abstract In this paper, we first propose a novel method for transferring material transformations across different scenes. Building on disentangled Neural Radiance Field (NeRF) representations, our approach learns to map Bidirectional Reflectance Distribution Functions (BRDF) from pairs of scenes observed in varying conditions, such as dry and wet. The learned transformations can then be applied to unseen scenes with similar materials, therefore effectively rendering the transformation learned with an arbitrary level of intensity. Extensive experiments on synthetic scenes and real‐world objects validate the effectiveness of our approach, showing that it can learn various transformations such as wetness, painting, coating, etc. Our results highlight not only the versatility of our method but also its potential for practical applications in computer graphics. We publish our method implementation, along with our synthetic/real datasets on https://github.com/astra‐vision/BRDFTransform

Progress in lighting estimation is tracked by computing existing image quality assessment (IQA) metrics on images from standard datasets. While this may appear to be a reasonable approach, we demonstrate that doing so does not correlate to human preference when the estimated lighting is used to relight a virtual scene into a real photograph. To study this, we design a controlled psychophysical experiment where human observers must choose their preference amongst rendered scenes lit using a set of lighting estimation algorithms selected from the recent literature, and use it to analyse how these algorithms perform according to human perception. Then, we demonstrate that none of the most popular IQA metrics from the literature, taken individually, correctly represent human perception. Finally, we show that by learning a combination of existing IQA metrics, we can more accurately represent human preference. This provides a new perceptual framework to help evaluate future lighting estimation algorithms. To encourage future research, all (anonymised) perceptual data and code are available at https://lvsn.github.io/PerceptionMetric/.

Abstract Relighting radiance fields is severely underconstrained for multi‐view data, which is most often captured under a single illumination condition; It is especially hard for full scenes containing multiple objects. We introduce a method to create relightable radiance fields using such single‐illumination data by exploiting priors extracted from 2D image diffusion models. We first fine‐tune a 2D diffusion model on a multi‐illumination dataset conditioned by light direction, allowing us to augment a single‐illumination capture into a realistic – but possibly inconsistent – multi‐illumination dataset from directly defined light directions. We use this augmented data to create a relightable radiance field represented by 3D Gaussian splats. To allow direct control of light direction for low‐frequency lighting, we represent appearance with a multi‐layer perceptron parameterized on light direction. To enforce multi‐view consistency and overcome inaccuracies we optimize a per‐image auxiliary feature vector. We show results on synthetic and real multi‐view data under single illumination, demonstrating that our method successfully exploits 2D diffusion model priors to allow realistic 3D relighting for complete scenes.

Most camera lens systems are designed in isolation, separately from downstream computer vision methods. Recently, joint optimization approaches that design lenses alongside other components of the image acquisition and processing pipeline—notably, downstream neural networks—have achieved improved imaging quality or better performance on vision tasks. However, these existing methods optimize only a subset of lens parameters and cannot optimize glass materials given their categorical nature. In this work, we develop a differentiable spherical lens simulation model that accurately captures geometrical aberrations. We propose an optimization strategy to address the challenges of lens design—notorious for non-convex loss function landscapes and many manufacturing constraints—that are exacerbated in joint optimization tasks. Specifically, we introduce quantized continuous glass variables to facilitate the optimization and selection of glass materials in an end-to-end design context, and couple this with carefully designed constraints to support manufacturability. In automotive object detection, we report improved detection performance over existing designs even when simplifying designs to two- or three-element lenses, despite significantly degrading the image quality.

GAN-based image restoration inverts the generative process to repair images corrupted by known degradations. Existing unsupervised methods must be carefully tuned for each task and degradation level. In this work, we make StyleGAN image restoration robust: a single set of hyperparameters works across a wide range of degradation levels. This makes it possible to handle combinations of several degradations, without the need to retune. Our proposed approach relies on a 3-phase progressive latent space extension and a conservative optimizer, which avoids the need for any additional regularization terms. Extensive experiments demonstrate robustness on inpainting, upsampling, denoising, and deartifacting at varying degradations levels, outperforming other StyleGAN-based inversion techniques. Our approach also favorably compares to diffusion-based restoration by yielding much more realistic inversion results. Code is available at the above URL.

Wide-angle lenses are commonly used in perception tasks requiring a large field of view. Unfortunately, these lenses produce significant distortions making conventional models that ignore the distortion effects unable to adapt to wide-angle images. In this paper, we present a novel transformer-based model that automatically adapts to the distortion produced by wide-angle lenses. We leverage the physical characteristics of such lenses, which are analytically defined by the radial distortion profile (assumed to be known), to develop a distortion aware radial swin transformer (DarSwin). In contrast to conventional transformer-based architectures, DarSwin comprises a radial patch partitioning, a distortion-based sampling technique for creating token embeddings, and an angular position encoding for radial patch merging. We validate our method on classification tasks using synthetically distorted ImageNet data and show through extensive experiments that DarSwin can perform zero-shot adaptation to unseen distortions of different wide-angle lenses. Compared to other baselines, DarSwin achieves the best results (in terms of Top-1 accuracy) with significant gains when trained on bounded levels of distortions (very-low, low, medium, and high) and tested on all including out-of-distribution distortions. The code and models are publicly available at https://lvsn.github.io/darswin/

Light plays an important role in human well-being. However, most computer vision tasks treat pixels without considering their relationship to physical luminance. To address this shortcoming, we introduce the Laval Photometric Indoor HDR Dataset, the first large-scale photometrically calibrated dataset of high dynamic range 360° panoramas. Our key contribution is the calibration of an existing, uncalibrated HDR Dataset. We do so by accurately capturing RAW bracketed exposures simultaneously with a professional photometric measurement device (chroma meter) for multiple scenes across a variety of lighting conditions. Using the resulting measurements, we establish the calibration coefficients to be applied to the HDR images. The resulting dataset is a rich representation of indoor scenes which displays a wide range of illuminance and color, and varied types of light sources. We exploit the dataset to introduce three novel tasks, where: per-pixel luminance, per-pixel color and planar illuminance can be predicted from a single input image. Finally, we also capture another smaller photometric dataset with a commercial 360° camera, to experiment on generalization across cameras. We are optimistic that the release of our datasets and associated code will spark interest in physically accurate light estimation within the community. Dataset and code are available at https://lvsn.github.io/beyondthepixel/.

Because of the diversity in lighting environments, existing illumination estimation techniques have been designed explicitly on indoor or outdoor environments. Methods have focused specifically on capturing accurate energy (e.g., through parametric lighting models), which emphasizes shading and strong cast shadows; or producing plausible texture (e.g., with GANs), which prioritizes plausible reflections. Approaches which provide editable lighting capabilities have been proposed, but these tend to be with simplified lighting models, offering limited realism. In this work, we propose to bridge the gap between these recent trends in the literature, and propose a method which combines a parametric light model with 360° panoramas, ready to use as HDRI in rendering engines. We leverage recent advances in GAN-based LDR panorama extrapolation from a regular image, which we extend to HDR using parametric spherical gaussians. To achieve this, we introduce a novel lighting co-modulation method that injects lighting-related features throughout the generator, tightly coupling the original or edited scene illumination within the panorama generation process. In our representation, users can easily edit light direction, intensity, number, etc. to impact shading while providing rich, complex reflections while seamlessly blending with the edits. Furthermore, our method encompasses indoor and outdoor environments, demonstrating state-of-the-art results even when compared to domain-specific methods.

We present a method to estimate the depth of field effect from a single image. Most existing methods related to this task provide either a per-pixel estimation of blur and/or depth. Instead, we go further and propose to use a lens-based representation that models the depth of field using two parameters: the blur factor and focus disparity. Those two parameters, along with the signed defocus representation, result in a more intuitive and linear representation which we solve using a novel weighting network. Furthermore, our method explicitly enforces consistency between the estimated defocus blur, the lens parameters, and the depth map. Finally, we train our deep-learning-based model on a mix of real images with synthetic depth of field and fully synthetic images. These improvements result in a more robust and accurate method, as demonstrated by our state-of-the-art results. In particular, our lens parametrization enables several applications, such as 3D staging for AR environments and seamless object compositing.

Compositing virtual objects into real background images requires one to carefully match the scene’s camera parameters, surface geometry, textures, and lighting to obtain plausible renderings. Recent learning approaches have shown many scene properties can be estimated from images, resulting in robust automatic single-image compositing systems, but many challenges remain. In particular, interactions between real and synthetic shadows are not handled gracefully by existing methods, which typically assume a shadow-free background. As a result, they tend to generate double shadows when the synthetic object’s cast shadow overlaps a background shadow, and ignore shadows from the background that should be cast onto the synthetic object. In this paper, we present a compositing method for outdoor scenes that addresses these issues and produces realistic cast shadows. This requires identifying existing shadows, including soft shadow boundaries, then reasoning about the ambiguity of unknown ground albedo and scene lighting to match the color and intensity of shaded areas. Using supervision from shadow removal and detection datasets, we propose a generative adversarial pipeline and improved composition equations that simultaneously handle both shadow interaction scenarios. We evaluate our method on challenging, real outdoor images from multiple distributions and datasets. Quantitative and qualitative comparisons show our approach produces more realistic results than existing alternatives. Our code, datasets, and trained models are publicly available at https://lvsn.github.io/shadowcompositing.

Image editing and compositing have become ubiquitous in entertainment, from digital art to AR and VR experiences. To produce beautiful composites, the camera needs to be geometrically calibrated, which can be tedious and requires a physical calibration target. In place of the traditional multi-image calibration process, we propose to infer the camera calibration parameters such as pitch, roll, field of view, and lens distortion directly from a single image using a deep convolutional neural network. We train this network using automatically generated samples from a large-scale panorama dataset, yielding competitive accuracy in terms of standard$\ell ^{2}$error. However, we argue that minimizing such standard error metrics might not be optimal for many applications. In this work, we investigate human sensitivity to inaccuracies in geometric camera calibration. To this end, we conduct a large-scale human perception study where we ask participants to judge the realism of 3D objects composited with correct and biased camera calibration parameters. Based on this study, we develop a new perceptual measure for camera calibration and demonstrate that our deep calibration network outperforms previous single-image based calibration methods both on standard metrics as well as on this novel perceptual measure. Finally, we demonstrate the use of our calibration network for several applications, including virtual object insertion, image retrieval, and compositing.

We propose a method to extrapolate a 360° field of view from a single image that allows for user-controlled synthesis of the out-painted content. To do so, we propose improvements to an existing GAN-based in-painting architecture for out-painting panoramic image representation. Our method obtains state-of-the-art results and outperforms previous methods on standard image quality metrics. To allow controlled synthesis of out-painting, we introduce a novel guided co-modulation framework, which drives the image generation process with a common pretrained discriminative model. Doing so maintains the high visual quality of generated panoramas while enabling user-controlled semantic content in the extrapolated field of view. We demonstrate the state-of-the-art results of our method on field of view extrapolation both qualitatively and quantitatively, providing thorough analysis of our novel editing capabilities. Finally, we demonstrate that our approach benefits the photorealistic virtual insertion of highly glossy objects in photographs.

In image classification, it is common practice to train deep networks to extract a single feature vector per input image. Few-shot classification methods also mostly follow this trend. In this work, we depart from this established direction and instead propose to extract sets of feature vectors for each image. We argue that a set-based representation intrinsically builds a richer representation of images from the base classes, which can subsequently better transfer to the few-shot classes. To do so, we propose to adapt existing feature extractors to instead produce sets of feature vectors from images. Our approach, dubbed SetFeat, embeds shallow self-attention mechanisms inside existing encoder architectures. The attention modules are lightweight, and as such our method results in encoders that have approximately the same number of parameters as their original versions. During training and inference, a set-to-set matching metric is used to perform image classification. The effectiveness of our proposed architecture and metrics is demonstrated via thorough experiments on standard few-shot datasets-namely miniImageNet, tieredImageNet, and CUB-in both the 1- and 5-shot scenarios. In all cases but one, our method outperforms the state-of-the-art.

Scene inference under low-light is a challenging problem due to severe noise in the captured images. One way to reduce noise is to use longer exposure during the capture. However, in the presence of motion (scene or camera motion), longer exposures lead to motion blur, resulting in loss of image information. This creates a trade-off between these two kinds of image degradations: motion blur (due to long exposure) vs. noise (due to short exposure), also referred as a dual image corruption pair in this paper. With the rise of cameras capable of capturing multiple exposures of the same scene simultaneously, it is possible to overcome this trade-off. Our key observation is that although the amount and nature of degradation varies for these different image captures, the semantic content remains the same across all images. To this end, we propose a method to leverage these multi exposure captures for robust inference under low-light and motion. Our method builds on a feature consistency loss to encourage similar results from these individual captures, and uses the ensemble of their final predictions for robust visual recognition. We demonstrate the effectiveness of our approach on simulated images as well as real captures with multiple exposures, and across the tasks of object detection and image classification. Project: https://wisionlab.com/project/noiseblurdual

We introduce Mixture-based Feature Space Learning (MixtFSL) for obtaining a rich and robust feature representation in the context of few-shot image classification. Previous works have proposed to model each base class either with a single point or with a mixture model by relying on offline clustering algorithms. In contrast, we propose to model base classes with mixture models by simultaneously training the feature extractor and learning the mixture model parameters in an online manner. This results in a richer and more discriminative feature space which can be employed to classify novel examples from very few samples. Two main stages are proposed to train the MixtFSL model. First, the multimodal mixtures for each base class and the feature extractor parameters are learned using a combination of two loss functions. Second, the resulting network and mixture models are progressively refined through a leader-follower learning procedure, which uses the current estimate as a "target" network. This target network is used to make a consistent assignment of instances to mixture components, which increases performance and stabilizes training. The effectiveness of our end-to-end feature space learning approach is demonstrated with extensive experiments on four standard datasets and four backbones. Notably, we demon-strate that when we combine our robust representation with recent alignment-based approaches, we achieve new state-of-the-art results in the inductive setting, with an absolute accuracy for 5-shot classification of 82.45% on miniImageNet, 88.20% with tieredImageNet, and 60.70% in FC100 using the ResNet-12 backbone.

Much of the focus in the object detection literature has been on the problem of identifying the bounding box of a particular class of object in an image. Yet, in contexts such as robotics and augmented reality, it is often necessary to find a specific object instance-a unique toy or a custom industrial part for example-rather than a generic object class. Here, applications can require a rapid shift from one object instance to another, thus requiring fast turnaround which affords little-to-no training time. What is more, gathering a dataset and training a model for every new object instance to be detected can be an expensive and time-consuming process. In this context, we propose a generic 2D object instance detection approach that uses example viewpoints of the target object at test time to retrieve its 2D location in RGB images, without requiring any additional training (i.e. fine-tuning) step. To this end, we present an end-to-end architecture that extracts global and local information of the object from its viewpoints. The global information is used to tune early filters in the backbone while local viewpoints are correlated with the input image. Our method offers an improvement of almost 30 mAP over the previous template matching methods on the challenging Occluded Linemod [3] dataset (overall mAP of 50.7). Our experiments also show that our single generic model (not trained on any of the test objects) yields detection results that are on par with approaches that are trained specifically on the target objects.

Photometric Stereo (PS) under outdoor illumination remains a challenging, ill-posed problem due to insufficient variability in illumination. Months-long capture sessions are typically used in this setup, with little success on shorter, single-day time intervals. In this paper, we investigate the solution of outdoor PS over a single day, under different weather conditions. First, we investigate the relationship between weather and surface reconstructability in order to understand when natural lighting allows existing PS algorithms to work. Our analysis reveals that partially cloudy days improve the conditioning of the outdoor PS problem while sunny days do not allow the unambiguous recovery of surface normals from photometric cues alone. We demonstrate that calibrated PS algorithms can thus be employed to reconstruct Lambertian surfaces accurately under partially cloudy days. Second, we solve the ambiguity arising in clear days by combining photometric cues with prior knowledge on material properties, local surface geometry and the natural variations in outdoor lighting through a CNN-based, weakly-calibrated PS technique. Given a sequence of outdoor images captured during a single sunny day, our method robustly estimates the scene surface normals with unprecedented quality for the considered scenario. Our approach does not require precise geolocation and significantly outperforms several state-of-the-art methods on images with real lighting, showing that our CNN can combine efficiently learned priors and photometric cues available during a single sunny day.

Most modern commodity imaging systems we use directly for photography—or indirectly rely on for downstream applications—employ optical systems of multiple lenses that must balance deviations from perfect optics, manufacturing constraints, tolerances, cost, and footprint. Although optical designs often have complex interactions with downstream image processing or analysis tasks, today’s compound optics are designed in isolation from these interactions. Existing optical design tools aim to minimize optical aberrations, such as deviations from Gauss’ linear model of optics, instead of application-specific losses, precluding joint optimization with hardware image signal processing (ISP) and highly parameterized neural network processing. In this article, we propose an optimization method for compound optics that lifts these limitations. We optimize entire lens systems jointly with hardware and software image processing pipelines, downstream neural network processing, and application-specific end-to-end losses. To this end, we propose a learned, differentiable forward model for compound optics and an alternating proximal optimization method that handles function compositions with highly varying parameter dimensions for optics, hardware ISP, and neural nets. Our method integrates seamlessly atop existing optical design tools, such as Zemax . We can thus assess our method across many camera system designs and end-to-end applications. We validate our approach in an automotive camera optics setting—together with hardware ISP post processing and detection—outperforming classical optics designs for automotive object detection and traffic light state detection. For human viewing tasks, we optimize optics and processing pipelines for dynamic outdoor scenarios and dynamic low-light imaging. We outperform existing compartmentalized design or fine-tuning methods qualitatively and quantitatively, across all domain-specific applications tested.

Recent work has demonstrated that deep learning approaches can successfully be used to recover accurate estimates of the spatially-varying BRDF (SVBRDF) of a surface from as little as a single image. Closer inspection reveals, however, that most approaches in the literature are trained purely on synthetic data, which, while diverse and realistic, is often not representative of the richness of the real world. In this paper, we show that training such networks exclusively on synthetic data is insufficient to achieve adequate results when tested on real data. Our analysis leverages a new dataset of real materials obtained with a novel portable multi-light capture apparatus. Through an extensive series of experiments and with the use of a novel deep learning architecture, we explore two strategies for improving results on real data: finetuning, and a per-material optimization procedure. We show that adapting network weights to real data is of critical importance, resulting in an approach which significantly outperforms previous methods for SVBRDF estimation on real materials. Dataset and code are available at https://lvsn.github.io/ real-svbrdf.

Relighting is an essential step in realistically transferring objects from a captured image into another environment. For example, authentic telepresence in Augmented Reality requires faces to be displayed and relit consistent with the observer's scene lighting. We investigate end-to-end deep learning architectures that both de-light and relight an image of a human face. Our model decomposes the input image into intrinsic components according to a diffuse physics-based image formation model. We enable non-diffuse effects including cast shadows and specular highlights by predicting a residual correction to the diffuse render. To train and evaluate our model, we collected a portrait database of 21 subjects with various expressions and poses. Each sample is captured in a controlled light stage setup with 32 individual light sources. Our method creates precise and believable relighting results and generalizes to complex illumination conditions and challenging poses, including when the subject is not looking straight at the camera.

Computer vision datasets containing multiple modalities such as color, depth, and thermal properties are now commonly accessible and useful for solving a wide array of challenging tasks. However, deploying multi-sensor heads is not possible in many scenarios. As such many practical solutions tend to be based on simpler sensors, mostly for cost, simplicity and robustness considerations. In this work, we propose a training methodology to take advantage of these additional modalities available in datasets, even if they are not available at test time. By assuming that the modalities have a strong spatial correlation, we propose Input Dropout, a simple technique that consists in stochastic hiding of one or many input modalities at training time, while using only the canonical (e.g. RGB) modalities at test time. We demonstrate that Input Dropout trivially combines with existing deep convolutional architectures, and improves their performance on a wide range of computer vision tasks such as dehazing, 6-DOF object tracking, pedestrian detection and object classification.

Augmented reality devices require multiple sensors to perform various tasks such as localization and tracking. Currently, popular cameras are mostly frame-based (e.g. RGB and Depth) which impose a high data bandwidth and power usage. With the necessity for low power and more responsive augmented reality systems, using solely frame-based sensors imposes limits to the various algorithms that needs high frequency data from the environement. As such, event-based sensors have become increasingly popular due to their low power, bandwidth and latency, as well as their very high frequency data acquisition capabilities. In this paper, we propose, for the first time, to use an event-based camera to increase the speed of 3D object tracking in 6 degrees of freedom. This application requires handling very high object speed to convey compelling AR experiences. To this end, we propose a new system which combines a recent RGB-D sensor (Kinect Azure) with an event camera (DAVIS346). We develop a deep learning approach, which combines an existing RGB-D network along with a novel event-based network in a cascade fashion, and demonstrate that our approach significantly improves the robustness of a state-of-the-art frame-based 6-DOF object tracker using our RGB-D-E pipeline. Our code and our RGB-D-E evaluation dataset are available at https://github.com/lvsn/rgbde-tracking.

We propose a real-time method to estimate spatially-varying indoor lighting from a single RGB image. Given an image and a 2D location in that image, our CNN estimates a 5th order spherical harmonic representation of the lighting at the given location in less than 20ms on a laptop mobile graphics card. While existing approaches estimate a single, global lighting representation or require depth as input, our method reasons about local lighting without requiring any geometry information. We demonstrate, through quantitative experiments including a user study, that our results achieve lower lighting estimation errors and are preferred by users over the state-of-the-art. Our approach can be used directly for augmented reality applications, where a virtual object is relit realistically at any position in the scene in real-time.

We propose a data-driven learned sky model, which we use for outdoor lighting estimation from a single image. As no large-scale dataset of images and their corresponding ground truth illumination is readily available, we use complementary datasets to train our approach, combining the vast diversity of illumination conditions of SUN360 with the radiometrically calibrated and physically accurate Laval HDR sky database. Our key contribution is to provide a holistic view of both lighting modeling and estimation, solving both problems end-to-end. From a test image, our method can directly estimate an HDR environment map of the lighting without relying on analytical lighting models. We demonstrate the versatility and expressivity of our learned sky model and show that it can be used to recover plausible illumination, leading to visually pleasant virtual object insertions. To further evaluate our method, we capture a dataset of HDR 360° panoramas and show through extensive validation that we significantly outperform previous state-of-the-art.

We present a neural network that predicts HDR outdoor illumination from a single LDR image. At the heart of our work is a method to accurately learn HDR lighting from LDR panoramas under any weather condition. We achieve this by training another CNN (on a combination of synthetic and real images) to take as input an LDR panorama, and regress the parameters of the Lalonde-Mathews outdoor illumination model. This model is trained such that it a) reconstructs the appearance of the sky, and b) renders the appearance of objects lit by this illumination. We use this network to label a large-scale dataset of LDR panoramas with lighting parameters and use them to train our single image outdoor lighting estimation network. We demonstrate, via extensive experiments, that both our panorama and singe image networks outperform the state of the art, and unlike prior work, are able to handle weather conditions ranging from fully sunny to overcast skies.

We present a method to estimate lighting from a single image of an indoor scene. Previous work has used an environment map representation that does not account for the localized nature of indoor lighting. Instead, we represent lighting as a set of discrete 3D lights with geometric and photometric parameters. We train a deep neural network to regress these parameters from a single image, on a dataset of environment maps annotated with depth. We propose a differentiable layer to convert these parameters to an environment map to compute our loss; this bypasses the challenge of establishing correspondences between estimated and ground truth lights. We demonstrate, via quantitative and qualitative evaluations, that our representation and training scheme lead to more accurate results compared to previous work, while allowing for more realistic 3D object compositing with spatially-varying lighting.

To improve the robustness to rain, we present a physically-based rain rendering pipeline for realistically inserting rain into clear weather images. Our rendering relies on a physical particle simulator, an estimation of the scene lighting and an accurate rain photometric modeling to augment images with arbitrary amount of realistic rain or fog. We validate our rendering with a user study, proving our rain is judged 40% more realistic that state-of-the-art. Using our generated weather augmented Kitti and Cityscapes dataset, we conduct a thorough evaluation of deep object detection and semantic segmentation algorithms and show that their performance decreases in degraded weather, on the order of 15% for object detection and 60% for semantic segmentation. Furthermore, we show refining existing networks with our augmented images improves the robustness of both object detection and semantic segmentation algorithms. We experiment on nuScenes and measure an improvement of 15% for object detection and 35% for semantic segmentation compared to original rainy performance. Augmented databases and code are available on the project page.

Nearly every commodity imaging system we directly interact with, or indirectly rely on, leverages power efficient, application-adjustable black-box hardware image signal processing (ISPs) units, running either in dedicated hardware blocks, or as proprietary software modules on programmable hardware. The configuration parameters of these black-box ISPs often have complex interactions with the output image, and must be adjusted prior to deployment according to application-specific quality and performance metrics. Today, this search is commonly performed manually by "golden eye" experts or algorithm developers leveraging domain expertise. We present a fully automatic system to optimize the parameters of black-box hardware and software image processing pipelines according to any arbitrary (i.e., application-specific) metric. We leverage a differentiable mapping between the configuration space and evaluation metrics, parameterized by a convolutional neural network that we train in an end-to-end fashion with imaging hardware in-the-loop. Unlike prior art, our differentiable proxies allow for high-dimension parameter search with stochastic first-order optimizers, without explicitly modeling any lower-level image processing transformations. As such, we can efficiently optimize black-box image processing pipelines for a variety of imaging applications, reducing application-specific configuration times from months to hours. Our optimization method is fully automatic, even with black-box hardware in the loop. We validate our method on experimental data for real-time display applications, object detection, and extreme low-light imaging. The proposed approach outperforms manual search qualitatively and quantitatively for all domain-specific applications tested. When applied to traditional denoisers, we demonstrate that---just by changing hyperparameters---traditional algorithms can outperform recent deep learning methods by a substantial margin on recent benchmarks.

In this work, we propose a step towards a more accurate prediction of the environment light given a single picture of a known object. To achieve this, we develop a deep learning method that is able to encode the latent space of indoor lighting using few parameters that is trained on a database of environment maps. This latent space is then used to generate predictions of the light that are both more realistic and accurate than previous methods. Our first contribution is a deep autoencoder which is capable of learning the feature space that compactly models lighting. Our second contribution is a convolutional neural network that predicts the light from a single image of a known object. To train these networks, our third contribution is a novel dataset that contains 21,000 HDR indoor environment maps. Finally, we evaluate our method on a dataset of synthetic objects and find it to outperform the state-of-the-art techniques across a variety of materials and poses.

Most current single image camera calibration methods rely on specific image features or user input, and cannot be applied to natural images captured in uncontrolled settings. We propose directly inferring camera calibration parameters from a single image using a deep convolutional neural network. This network is trained using automatically generated samples from a large-scale panorama dataset, and considerably outperforms other methods, including recent deep learning-based approaches, in terms of standard L2 error. However, we argue that in many cases it is more important to consider how humans perceive errors in camera estimation. To this end, we conduct a large-scale human perception study where we ask users to judge the realism of 3D objects composited with and without ground truth camera calibration. Based on this study, we develop a new perceptual measure for camera calibration, and demonstrate that our deep calibration network outperforms other methods on this measure. Finally, we demonstrate the use of our calibration network for a number of applications including virtual object insertion, image retrieval and compositing.

Abstract Image‐based lighting has allowed the creation of photo‐realistic computer‐generated content. However, it requires the accurate capture of the illumination conditions, a task neither easy nor intuitive, especially to the average digital photography enthusiast. This paper presents an approach to directly estimate an HDR light probe from a single LDR photograph, shot outdoors with a consumer camera, without specialized calibration targets or equipment. Our insight is to use a person's face as an outdoor light probe. To estimate HDR light probes from LDR faces we use an inverse rendering approach which employs data‐driven priors to guide the estimation of realistic, HDR lighting. We build compact, realistic representations of outdoor lighting both parametrically and in a data‐driven way, by training a deep convolutional autoencoder on a large dataset of HDR sky environment maps. Our approach can recover high‐frequency, extremely high dynamic range lighting environments. For quantitative evaluation of lighting estimation accuracy and relighting accuracy, we also contribute a new database of face photographs with corresponding HDR light probes. We show that relighting objects with HDR light probes estimated by our method yields realistic results in a wide variety of settings.

We present a convolutional neural network-based (CNN-based) technique to estimate high-dynamic range outdoor illumination from a single low dynamic range image. To train the CNN, we leverage a large dataset of outdoor panoramas. We fit a low-dimensional physically-based outdoor illumination model to the skies in these panoramas giving us a compact set of parameters (including sun position, atmospheric conditions, and camera parameters). We extract limited field-of-view images from the panoramas, and train a CNN with this large set of input image–output lighting parameter pairs. Given a test image, this network can be used to infer illumination parameters that can, in turn, be used to reconstruct an outdoor illumination environment map. We demonstrate that our approach allows the recovery of plausible illumination conditions and enables photorealistic virtual object insertion from a single image. An extensive evaluation on both the panorama dataset and captured HDR environment maps shows that our technique significantly outperforms previous solutions to this problem.

Outdoor lighting has extremely high dynamic range. This makes the process of capturing outdoor environment maps notoriously challenging since special equipment must be used. In this work, we propose an alternative approach. We first capture lighting with a regular, LDR omnidirectional camera, and aim to recover the HDR after the fact via a novel, learning-based inverse tonemapping method. We propose a deep autoencoder framework which regresses linear, high dynamic range data from non-linear, saturated, low dynamic range panoramas. We validate our method through a wide set of experiments on synthetic data, as well as on a novel dataset of real photographs with ground truth. Our approach finds applications in a variety of settings, ranging from outdoor light capture to image matching.

We propose a deep learning framework to analyse the uncertainty associated with dyadic human activities at a small temporal granularity. Such time-slice analysis is able to infer human behaviours from short-term observations. Instead of classifying time-slices into k classes of activities, we report to what degree of certainty each activity is occurring from definitely not occurring to definitely occurring. To this end, we extract CNN-based unary probabilities and pairwise relations between body joints. The unary term gives cues on the local appearance while the pairwise term captures the contextual relations between the parts. We extract the features from each frame in a timeslice and examine different temporal aggregation schemes to generate a descriptor for the whole time-slice. Evaluations on the TAP dataset which is well-suited for time-slice activity analysis demonstrate the effectiveness of our approach for the task of uncertainty analysis in activity prediction.

We propose an automatic method to infer high dynamic range illumination from a single, limited field-of-view, low dynamic range photograph of an indoor scene. In contrast to previous work that relies on specialized image capture, user input, and/or simple scene models, we train an end-to-end deep neural network that directly regresses a limited field-of-view photo to HDR illumination, without strong assumptions on scene geometry, material properties, or lighting. We show that this can be accomplished in a three step process: 1) we train a robust lighting classifier to automatically annotate the location of light sources in a large dataset of LDR environment maps, 2) we use these annotations to train a deep neural network that predicts the location of lights in a scene from a single limited field-of-view photo, and 3) we fine-tune this network using a small dataset of HDR environment maps to predict light intensities. This allows us to automatically recover high-quality HDR illumination estimates that significantly outperform previous state-of-the-art methods. Consequently, using our illumination estimates for applications like 3D object insertion, produces photo-realistic results that we validate via a perceptual user study.

We present a temporal 6-DOF tracking method which leverages deep learning to achieve state-of-the-art performance on challenging datasets of real world capture. Our method is both more accurate and more robust to occlusions than the existing best performing approaches while maintaining real-time performance. To assess its efficacy, we evaluate our approach on several challenging RGBD sequences of real objects in a variety of conditions. Notably, we systematically evaluate robustness to occlusions through a series of sequences where the object to be tracked is increasingly occluded. Finally, our approach is purely data-driven and does not require any hand-designed features: robust tracking is automatically learned from data.

While Photometric Stereo (PS) has long been confined to the lab, there has been a recent interest in applying this technique to reconstruct outdoor objects and scenes. Un-fortunately, the most successful outdoor PS techniques typically require gathering either months of data, or waiting for a particular time of the year. In this paper, we analyze the illumination requirements for single-day outdoor PS to yield stable normal reconstructions, and determine that these requirements are often available in much less than a full day. In particular, we show that the right set of conditions for stable PS solutions may be observed in the sky within short time intervals of just above one hour. This work provides, for the first time, a detailed analysis of the factors affecting the performance of x-hour outdoor photometric stereo.

Existing tone mapping operators (TMOs) provide good results in well-lit scenes, but often perform poorly on im-ages in low light conditions. In these scenes, noise is prevalent and gets amplified by TMOs, as they confuse contrast created by noise with contrast created by the scene. This paper presents a principled approach to produce tone mapped images with less visible noise. For this purpose, we leverage established models of camera noise and human contrast perception to design two new quality scores: contrast waste and contrast loss, which measure image quality as a function of contrast allocation. To produce tone mappings with less visible noise, we apply these scores in two ways: first, to automatically tune the parameters of existing TMOs to reduce the amount of noise they produce; and second, to propose a new noise-aware tone curve

Photometric Stereo has been explored extensively in laboratory conditions since its inception. Recently, attempts have been made at applying this technique under natural outdoor lighting. Outdoor photometric stereo presents additional challenges as one does not have control over illumination anymore. In this paper, we explore the stability of surface normals reconstructed outdoors. We present a data-driven analysis based on a large database of outdoor HDR environment maps. Given a sequence of object images and corresponding sky maps captured in a single day, we investigate natural factors that impact the uncertainty in the estimated surface normals. Quantitative evidence reveals strong dependencies between expected accuracy and the normal orientation, cloud coverage, and sun elevation. In particular, we show that partially cloudy days yield greater accuracy than sunny days with clear skies; furthermore, high sun elevation--recommended in previous work--is in fact not necessarily optimal when taking more elaborate illumination models into account.

It is known that humans can be insensitive to large changes in illumination. For example, if an object of interest is extracted from one digital photograph and inserted into another, we do not always notice the differences in illumination between the object and its new background. This inability to spot illumination inconsistencies is often the key to success in digital “doctoring” operations. We present a set of experiments in which we explore the perception of illumination in outdoor scenes. Our results can be used to predict when and why inconsistencies go unnoticed. Applications of the knowledge gained from our studies include smarter digital “cut-and-paste” and digital “fake” detection tools, and image-based composite scene backgrounds for layout and previsualization.

Large scale structure-from-motion (SfM) algorithms have recently enabled the reconstruction of highly detailed 3-D models of our surroundings simply by taking photographs. In this paper, we propose to leverage these reconstruction techniques to automatically estimate the outdoor illumination conditions for each image in a SfM photo collection. We introduce a novel dataset of outdoor photo collections, where the ground truth lighting conditions are known at each image. We also present an inverse rendering approach that recovers a high dynamic range estimate of the lighting conditions for each low dynamic range input image. Our novel database is used to quantitatively evaluate the performance of our algorithm. Results show that physically plausible lighting estimates can faithfully be recovered, both in terms of light direction and intensity.

Given a single outdoor image, we present a method for estimating the likely illumination conditions of the scene. In particular, we compute the probability distribution over the sun position and visibility. The method relies on a combination of weak cues that can be extracted from different portions of the image: the sky, the vertical surfaces, and the ground. While no single cue can reliably estimate illumination by itself, each one can reinforce the others to yield a more robust estimate. This is combined with a data-driven prior computed over a dataset of 6 million Internet photos. We present quantitative results on a webcam dataset with annotated sun positions, as well as qualitative results on consumer-grade photographs downloaded from Internet. Based on the estimated illumination, we show how to realistically insert synthetic 3-D objects into the scene.

Webcams placed all over the world observe and record the visual appearance of a variety of outdoor scenes over long periods of time. The recorded time-lapse image sequences cover a wide range of illumination and weather conditions -- a vast untapped resource for creating visual realism. In this work, we propose to use a large repository of webcams as a "clip art" library from which users may transfer scene appearance (objects, scene backdrops, outdoor illumination) into their own time-lapse sequences or even single photographs. The goal is to combine the recent ideas from data-driven appearance transfer techniques with a general and theoretically-grounded physically-based illumination model. To accomplish this, the paper presents three main research contributions: 1) a new, high-quality outdoor webcam database that has been calibrated radiometrically and geometrically; 2) a novel approach for matching illuminations across different scenes based on the estimation of the properties of natural illuminants (sun, sky, weather and clouds), the camera geometry, and illumination-dependent scene features; 3) a new algorithm for generating physically plausible high dynamic range environment maps for each frame in a webcam sequence.

Abstract Many categories of objects, such as human faces, can be naturally viewed as a composition of several different layers. For example, a bearded face with glasses can be decomposed into three layers: a layer for glasses, a layer for the beard and a layer for other permanent facial features. While modeling such a face with a linear subspace model could be very difficult, layer separation allows for easy modeling and modification of some certain structures while leaving others unchanged. In this paper, we present a method for automatic layer extraction and its applications to face synthesis and editing. Layers are automatically extracted by utilizing the differences between subspaces and modeled separately. We show that our method can be used for tasks such beard removal (virtual shaving), beard synthesis, and beard transfer, among others.

Why does placing an object from one photograph into another often make the colors of that object suddenly look wrong? One possibility is that humans prefer distributions of colors that are often found in nature; that is, we find pleasing these color combinations that we see often. Another possibility is that humans simply prefer colors to be consistent within an image, regardless of what they are. In this paper, we explore some of these issues by studying the color statistics of a large dataset of natural images, and by looking at differences in color distribution in realistic and unrealistic images. We apply our findings to two problems: 1) classifying composite images into realistic vs. non- realistic, and 2) recoloring image regions for realistic compositing.

In this paper, we present an approach for potential negative obstacle detection, based on missing data interpretation that extends traditional techniques driven by data only, which capture the occupancy of the scene. The approach is decomposed into three steps: three-dimensional (3D) data accumulation and low level classification, 3D occluder propagation, and context-based occlusion labeling. The approach is validated using logged laser data collected in various outdoor natural terrains and also demonstrated live on-board the Demo-III experimental unmanned vehicle (XUV).

We present a system for inserting new objects into existing photographs by querying a vast image-based object library, pre-computed using a publicly available Internet object database. The central goal is to shield the user from all of the arduous tasks typically involved in image compositing. The user is only asked to do two simple things: 1) pick a 3D location in the scene to place a new object; 2) select an object to insert using a hierarchical menu. We pose the problem of object insertion as a data-driven, 3D-based, context-sensitive object retrieval task. Instead of trying to manipulate the object to change its orientation, color distribution, etc. to fit the new image, we simply retrieve an object of a specified class that has all the required properties (camera pose, lighting, resolution, etc) from our large object library. We present new automatic algorithms for improving object segmentation and blending, estimating true 3D object size and orientation, and estimating scene lighting conditions. We also present an intuitive user interface that makes object insertion fast and simple even for the artistically challenged.

The mobile robot programming laboratory course has been taught at Carnegie Mellon University for the past twelve years. It is a problem-driven class designed for students with little or no experience with robots. In this paper, we first present the current status of the class, and show how it improves the education and training of students in a robotics curriculum by giving them a hands-on experience with a real robot. We show that, in addition to core subjects such as perception, action and cognition, students also have the opportunity to learn advanced topics such as reinforcement learning and multi-robot coordination. We then discuss the evolution of the class under general categories: hardware and programming environment, team experiments, and assignments. We present important lessons learned in each category, and how they affect the learning experience of participating students. We conclude by discussing future opportunities