M. Kowalski

George Stein, Uros Seljak, Vanessa Bohm et al. · uw

We construct a physically-parameterized probabilistic autoencoder (PAE) to learn the intrinsic diversity of type Ia supernovae (SNe Ia) from a sparse set of spectral time series. The PAE is a two-stage generative model, composed of an Auto-Encoder (AE) which is interpreted probabilistically after training using a Normalizing Flow (NF). We demonstrate that the PAE learns a low-dimensional latent space that captures the nonlinear range of features that exists within the population, and can accurately model the spectral evolution of SNe Ia across the full range of wavelength and observation times directly from the data. By introducing a correlation penalty term and multi-stage training setup alongside our physically-parameterized network we show that intrinsic and extrinsic modes of variability can be separated during training, removing the need for the additional models to perform magnitude standardization. We then use our PAE in a number of downstream tasks on SNe Ia for increasingly precise cosmological analyses, including automatic detection of SN outliers, the generation of samples consistent with the data distribution, and solving the inverse problem in the presence of noisy and incomplete data to constrain cosmological distance measurements. We find that the optimal number of intrinsic model parameters appears to be three, in line with previous studies, and show that we can standardize our test sample of SNe Ia with an RMS of $0.091 \pm 0.010$ mag, which corresponds to $0.074 \pm 0.010$ mag if peculiar velocity contributions are removed. Trained models and codes are released at \href{https://github.com/georgestein/suPAErnova}{github.com/georgestein/suPAErnova}

Stephan J. Garbin, Marek Kowalski, Virginia Estellers et al.

The recent increase in popularity of volumetric representations for scene reconstruction and novel view synthesis has put renewed focus on animating volumetric content at high visual quality and in real-time. While implicit deformation methods based on learned functions can produce impressive results, they are `black boxes' to artists and content creators, they require large amounts of training data to generalise meaningfully, and they do not produce realistic extrapolations outside the training data. In this work we solve these issues by introducing a volume deformation method which is real-time, easy to edit with off-the-shelf software and can extrapolate convincingly. To demonstrate the versatility of our method, we apply it in two scenarios: physics-based object deformation and telepresence where avatars are controlled using blendshapes. We also perform thorough experiments showing that our method compares favourably to both volumetric approaches combined with implicit deformation and methods based on mesh deformation.

N. Miranda, J. C. Freytag, J. Nordin et al.

With a rapidly rising number of transients detected in astronomy, classification methods based on machine learning are increasingly being employed. Their goals are typically to obtain a definitive classification of transients, and for good performance they usually require the presence of a large set of observations. However, well-designed, targeted models can reach their classification goals with fewer computing resources. This paper presents SNGuess, a model designed to find young extragalactic nearby transients with high purity. SNGuess works with a set of features that can be efficiently calculated from astronomical alert data. Some of these features are static and associated with the alert metadata, while others must be calculated from the photometric observations contained in the alert. Most of the features are simple enough to be obtained or to be calculated already at the early stages in the lifetime of a transient after its detection. We calculate these features for a set of labeled public alert data obtained over a time span of 15 months from the Zwicky Transient Facility (ZTF). The core model of SNGuess consists of an ensemble of decision trees, which are trained via gradient boosting. Approximately 88% of the candidates suggested by SNGuess from a set of alerts from ZTF spanning from April 2020 to August 2021 were found to be true relevant supernovae (SNe). For alerts with bright detections, this number ranges between 92% and 98%. Since April 2020, transients identified by SNGuess as potential young SNe in the ZTF alert stream are being published to the Transient Name Server (TNS) under the AMPEL_ZTF_NEW group identifier. SNGuess scores for any transient observed by ZTF can be accessed via a web service. The source code of SNGuess is publicly available.

Joanna Kaleta, Kacper Kania, Tomasz Trzcinski et al.

Decoupling lighting from geometry using unconstrained photo collections is notoriously challenging. Solving it would benefit many users as creating complex 3D assets takes days of manual labor. Many previous works have attempted to address this issue, often at the expense of output fidelity, which questions the practicality of such methods. We introduce LumiGauss - a technique that tackles 3D reconstruction of scenes and environmental lighting through 2D Gaussian Splatting. Our approach yields high-quality scene reconstructions and enables realistic lighting synthesis under novel environment maps. We also propose a method for enhancing the quality of shadows, common in outdoor scenes, by exploiting spherical harmonics properties. Our approach facilitates seamless integration with game engines and enables the use of fast precomputed radiance transfer. We validate our method on the NeRF-OSR dataset, demonstrating superior performance over baseline methods. Moreover, LumiGauss can synthesize realistic images for unseen environment maps. Our code: https://github.com/joaxkal/lumigauss.

Marek Kowalski, Zbigniew Nasarzewski, Grzegorz Galinski et al.

We present HoloFace, an open-source framework for face alignment, head pose estimation and facial attribute retrieval for Microsoft HoloLens. HoloFace implements two state-of-the-art face alignment methods which can be used interchangeably: one running locally and one running on a remote backend. Head pose estimation is accomplished by fitting a deformable 3D model to the landmarks localized using face alignment. The head pose provides both the rotation of the head and a position in the world space. The parameters of the fitted 3D face model provide estimates of facial attributes such as mouth opening or smile. Together the above information can be used to augment the faces of people seen by the HoloLens user, and thus their interaction. Potential usage scenarios include facial recognition, emotion recognition, eye gaze tracking and many others. We demonstrate the capabilities of our framework by augmenting the faces of people seen through the HoloLens with various objects and animations.

Jack Saunders, Charlie Hewitt, Yanan Jian et al.

Gaussian Splatting has changed the game for real-time photo-realistic rendering. One of the most popular applications of Gaussian Splatting is to create animatable avatars, known as Gaussian Avatars. Recent works have pushed the boundaries of quality and rendering efficiency but suffer from two main limitations. Either they require expensive multi-camera rigs to produce avatars with free-view rendering, or they can be trained with a single camera but only rendered at high quality from this fixed viewpoint. An ideal model would be trained using a short monocular video or image from available hardware, such as a webcam, and rendered from any view. To this end, we propose GASP: Gaussian Avatars with Synthetic Priors. To overcome the limitations of existing datasets, we exploit the pixel-perfect nature of synthetic data to train a Gaussian Avatar prior. By fitting this prior model to a single photo or video and fine-tuning it, we get a high-quality Gaussian Avatar, which supports 360$^\circ$ rendering. Our prior is only required for fitting, not inference, enabling real-time application. Through our method, we obtain high-quality, animatable Avatars from limited data which can be animated and rendered at 70fps on commercial hardware. See our project page (https://microsoft.github.io/GASP/) for results.

Kacper Kania, Stephan J. Garbin, Andrea Tagliasacchi et al.

Generating faithful visualizations of human faces requires capturing both coarse and fine-level details of the face geometry and appearance. Existing methods are either data-driven, requiring an extensive corpus of data not publicly accessible to the research community, or fail to capture fine details because they rely on geometric face models that cannot represent fine-grained details in texture with a mesh discretization and linear deformation designed to model only a coarse face geometry. We introduce a method that bridges this gap by drawing inspiration from traditional computer graphics techniques. Unseen expressions are modeled by blending appearance from a sparse set of extreme poses. This blending is performed by measuring local volumetric changes in those expressions and locally reproducing their appearance whenever a similar expression is performed at test time. We show that our method generalizes to unseen expressions, adding fine-grained effects on top of smooth volumetric deformations of a face, and demonstrate how it generalizes beyond faces.

Kacper Kania, Kwang Moo Yi, Marek Kowalski et al.

We extend neural 3D representations to allow for intuitive and interpretable user control beyond novel view rendering (i.e. camera control). We allow the user to annotate which part of the scene one wishes to control with just a small number of mask annotations in the training images. Our key idea is to treat the attributes as latent variables that are regressed by the neural network given the scene encoding. This leads to a few-shot learning framework, where attributes are discovered automatically by the framework, when annotations are not provided. We apply our method to various scenes with different types of controllable attributes (e.g. expression control on human faces, or state control in movement of inanimate objects). Overall, we demonstrate, to the best of our knowledge, for the first time novel view and novel attribute re-rendering of scenes from a single video.

Kacper Kania, Marek Kowalski, Tomasz Trzciński

The creation of plausible and controllable 3D human motion animations is a long-standing problem that requires a manual intervention of skilled artists. Current machine learning approaches can semi-automate the process, however, they are limited in a significant way: they can handle only a single trajectory of the expected motion that precludes fine-grained control over the output. To mitigate that issue, we reformulate the problem of future pose prediction into pose completion in space and time where multiple trajectories are represented as poses with missing joints. We show that such a framework can generalize to other neural networks designed for future pose prediction. Once trained in this framework, a model is capable of predicting sequences from any number of trajectories. We propose a novel transformer-like architecture, TrajeVAE, that builds on this idea and provides a versatile framework for 3D human animation. We demonstrate that TrajeVAE offers better accuracy than the trajectory-based reference approaches and methods that base their predictions on past poses. We also show that it can predict reasonable future poses even if provided only with an initial pose.

Stephan J. Garbin, Marek Kowalski, Matthew Johnson et al.

Recent work on Neural Radiance Fields (NeRF) showed how neural networks can be used to encode complex 3D environments that can be rendered photorealistically from novel viewpoints. Rendering these images is very computationally demanding and recent improvements are still a long way from enabling interactive rates, even on high-end hardware. Motivated by scenarios on mobile and mixed reality devices, we propose FastNeRF, the first NeRF-based system capable of rendering high fidelity photorealistic images at 200Hz on a high-end consumer GPU. The core of our method is a graphics-inspired factorization that allows for (i) compactly caching a deep radiance map at each position in space, (ii) efficiently querying that map using ray directions to estimate the pixel values in the rendered image. Extensive experiments show that the proposed method is 3000 times faster than the original NeRF algorithm and at least an order of magnitude faster than existing work on accelerating NeRF, while maintaining visual quality and extensibility.

Tadas Baltrusaitis, Erroll Wood, Virginia Estellers et al.

Analysis of faces is one of the core applications of computer vision, with tasks ranging from landmark alignment, head pose estimation, expression recognition, and face recognition among others. However, building reliable methods requires time-consuming data collection and often even more time-consuming manual annotation, which can be unreliable. In our work we propose synthesizing such facial data, including ground truth annotations that would be almost impossible to acquire through manual annotation at the consistency and scale possible through use of synthetic data. We use a parametric face model together with hand crafted assets which enable us to generate training data with unprecedented quality and diversity (varying shape, texture, expression, pose, lighting, and hair).

Stephan J. Garbin, Marek Kowalski, Matthew Johnson et al.

Generating photorealistic images of human faces at scale remains a prohibitively difficult task using computer graphics approaches. This is because these require the simulation of light to be photorealistic, which in turn requires physically accurate modelling of geometry, materials, and light sources, for both the head and the surrounding scene. Non-photorealistic renders however are increasingly easy to produce. In contrast to computer graphics approaches, generative models learned from more readily available 2D image data have been shown to produce samples of human faces that are hard to distinguish from real data. The process of learning usually corresponds to a loss of control over the shape and appearance of the generated images. For instance, even simple disentangling tasks such as modifying the hair independently of the face, which is trivial to accomplish in a computer graphics approach, remains an open research question. In this work, we propose an algorithm that matches a non-photorealistic, synthetically generated image to a latent vector of a pretrained StyleGAN2 model which, in turn, maps the vector to a photorealistic image of a person of the same pose, expression, hair, and lighting. In contrast to most previous work, we require no synthetic training data. To the best of our knowledge, this is the first algorithm of its kind to work at a resolution of 1K and represents a significant leap forward in visual realism.

Marek Kowalski, Stephan J. Garbin, Virginia Estellers et al.

Our ability to sample realistic natural images, particularly faces, has advanced by leaps and bounds in recent years, yet our ability to exert fine-tuned control over the generative process has lagged behind. If this new technology is to find practical uses, we need to achieve a level of control over generative networks which, without sacrificing realism, is on par with that seen in computer graphics and character animation. To this end we propose ConfigNet, a neural face model that allows for controlling individual aspects of output images in semantically meaningful ways and that is a significant step on the path towards finely-controllable neural rendering. ConfigNet is trained on real face images as well as synthetic face renders. Our novel method uses synthetic data to factorize the latent space into elements that correspond to the inputs of a traditional rendering pipeline, separating aspects such as head pose, facial expression, hair style, illumination, and many others which are very hard to annotate in real data. The real images, which are presented to the network without labels, extend the variety of the generated images and encourage realism. Finally, we propose an evaluation criterion using an attribute detection network combined with a user study and demonstrate state-of-the-art individual control over attributes in the output images.

Marek Kowalski, Jacek Naruniec, Tomasz Trzcinski

In this paper, we propose Deep Alignment Network (DAN), a robust face alignment method based on a deep neural network architecture. DAN consists of multiple stages, where each stage improves the locations of the facial landmarks estimated by the previous stage. Our method uses entire face images at all stages, contrary to the recently proposed face alignment methods that rely on local patches. This is possible thanks to the use of landmark heatmaps which provide visual information about landmark locations estimated at the previous stages of the algorithm. The use of entire face images rather than patches allows DAN to handle face images with large variation in head pose and difficult initializations. An extensive evaluation on two publicly available datasets shows that DAN reduces the state-of-the-art failure rate by up to 70%. Our method has also been submitted for evaluation as part of the Menpo challenge.