Browsing by Author "Laine, Samuli"

Filter results by typing the first few letters
Now showing 1 - 9 of 9
  • Disentangling random and cyclic effects in time-lapse sequences
    (2022-07-22) Härkönen, Erik; Aittala, Miika; Kynkäänniemi, Tuomas; Laine, Samuli; Aila, Timo; Lehtinen, Jaakko
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    Time-lapse image sequences offer visually compelling insights into dynamic processes that are too slow to observe in real time. However, playing a long time-lapse sequence back as a video often results in distracting flicker due to random effects, such as weather, as well as cyclic effects, such as the day-night cycle. We introduce the problem of disentangling time-lapse sequences in a way that allows separate, after-the-fact control of overall trends, cyclic effects, and random effects in the images, and describe a technique based on data-driven generative models that achieves this goal. This enables us to "re-render"the sequences in ways that would not be possible with the input images alone. For example, we can stabilize a long sequence to focus on plant growth over many months, under selectable, consistent weather. Our approach is based on Generative Adversarial Networks (GAN) that are conditioned with the time coordinate of the time-lapse sequence. Our architecture and training procedure are designed so that the networks learn to model random variations, such as weather, using the GAN's latent space, and to disentangle overall trends and cyclic variations by feeding the conditioning time label to the model using Fourier features with specific frequencies. We show that our models are robust to defects in the training data, enabling us to amend some of the practical difficulties in capturing long time-lapse sequences, such as temporary occlusions, uneven frame spacing, and missing frames.
  • Efficient physically-based shadow algorithms
    (2006-09-29) Laine, Samuli
     Doctoral dissertation (article-based)
    This research focuses on developing efficient algorithms for computing shadows in computer-generated images. A distinctive feature of the shadow algorithms presented in this thesis is that they produce correct, physically-based results, instead of giving approximations whose quality is often hard to ensure or evaluate. Light sources that are modeled as points without any spatial extent produce hard shadows with sharp boundaries. Shadow mapping is a traditional method for rendering such shadows. A shadow map is a depth buffer computed from the scene, using a point light source as the viewpoint. The finite resolution of the shadow map requires that its contents are resampled when determining the shadows on visible surfaces. This causes various artifacts such as incorrect self-shadowing and jagged shadow boundaries. A novel method is presented that avoids the resampling step, and provides exact shadows for every point visible in the image. The shadow volume algorithm is another commonly used algorithm for real-time rendering of hard shadows. This algorithm gives exact results and does not suffer from any resampling problems, but it tends to consume a lot of fillrate, which leads to performance problems. This thesis presents a new technique for locally choosing between two previous shadow volume algorithms with different performance characteristics. A simple criterion for making the local choices is shown to yield better performance than using either of the algorithms alone. Light sources with nonzero spatial extent give rise to soft shadows with smooth boundaries. A novel method is presented that transposes the classical processing order for soft shadow computation in offline rendering. Instead of casting shadow rays, the algorithm first conceptually collects every ray that would need to be cast, and then processes the shadow-casting primitives one by one, hierarchically finding the rays that are blocked. Another new soft shadow algorithm takes a different point of view into computing the shadows. Only the silhouettes of the shadow casters are used for determining the shadows, and an unintrusive execution model makes the algorithm practical for production use in offline rendering. The proposed techniques accelerate the computing of physically-based shadows in real-time and offline rendering. These improvements make it possible to use correct, physically-based shadows in a broad range of scenes that previous methods cannot handle efficiently enough.
  • Hemispherical rasterization of shadow maps
    (2010) Hakala, Erik
     School of Science | Master's thesis
    Hemispherical rasterization has many meaningful use cases of which one is shadow mapping for 180 degrees spot lights. On a hemisphere, the standard rasterization methods yield high error and usually require high tessellation to reach acceptable quality levels. In this thesis a method for analytic hemispherical rasterization on modern hardware is presented. The algorithm offers a good and hassle free solution with manageable performance. Also a quick look is taken at alternative approximative solution, which is then used as one of the reference techniques for the analytic method. Theory is further reinforced with an implementation and analysis of its performance characteristics. Finally, the method is concluded to be viable for interactive and off-line rendering applications.
  • A Hybrid Generator Architecture for Controllable Face Synthesis
    (2023-08-21) Mensah, Dann
     Perustieteiden korkeakoulu | Master's thesis
  • A Hybrid Generator Architecture for Controllable Face Synthesis
    (2023-07-23) Mensah, Dann; Kim, Nam Hee; Aittala, Miika; Laine, Samuli; Lehtinen, Jaakko
     A4 Artikkeli konferenssijulkaisussa
    Modern data-driven image generation models often surpass traditional graphics techniques in quality. However, while traditional modeling and animation tools allow precise control over the image generation process in terms of interpretable quantities - e.g., shapes and reflectances - endowing learned models with such controls is generally difficult. In the context of human faces, we seek a data-driven generator architecture that simultaneously retains the photorealistic quality of modern generative adversarial networks (GAN) and allows explicit, disentangled controls over head shapes, expressions, identity, background, and illumination. While our high-level goal is shared by a large body of previous work, we approach the problem with a different philosophy: We treat the problem as an unconditional synthesis task, and engineer interpretable inductive biases into the model that make it easy for the desired behavior to emerge. Concretely, our generator is a combination of learned neural networks and fixed-function blocks, such as a 3D morphable head model and texture-mapping rasterizer, and we leave it up to the training process to figure out how they should be used together. This greatly simplifies the training problem by removing the need for labeled training data; we learn the distributions of the independent variables that drive the model instead of requiring that their values are known for each training image. Furthermore, we need no contrastive or imitation learning for correct behavior. We show that our design successfully encourages the generative model to make use of the internal, interpretable representations in a semantically meaningful manner. This allows sampling of different aspects of the image independently, as well as precise control of the results by manipulating the internal state of the interpretable blocks within the generator. This enables, for instance, facial animation using traditional animation tools.
  • An Incremental Shaft Subdivision Algorithm for Computing Shadows and Visibility
    (2006) Laine, Samuli
     Helsinki University of Technology | Master's thesis
    Pehmeiden varjojen piirto on tärkeä tehtävä tietokonegrafiikassa. Pehmeitä varjoja muodostuu, kun valonlähdettä ei esitetä pisteenä vaan pintana, jolla on nollasta poikkeava pinta-ala. Fysikaalisesti oikeiden varjojen laskennassa pitää määrittää tarkasteltavan pinnan pisteeseen valonlähteestä saapuvan valon määrä. Tämä on yleisesti laskennallisesti raskasta, ja tehokkaat ratkaisumenetelmät ovat tarpeen, jotta kuvan muodostusaika pysyy siedettävänä. Useimmiten lähekkäisten pisteiden vastaanottamat varjot ovat likimain samanlaisia, ja valon- lähteen lähekkäiset osat myös vaikuttavat kuvaan enimmäkseen samalla tavalla. Modernit varjoalgoritmit perustuvat näiden koherenssin muotojen hyödyntämiseen. Tässä työssä esitellään uusi fysikaalisesti oikeiden pehmeiden varjojen laskenta-algoritmi, joka pyrkii hyödyntämään koherenssia niin paljon kuin mahdollista laskemalla varjorelaatiot suurissa ryhmissä sen sijaan, että tarkasteltaisiin yksittäisiä pisteitä valonlähteellä tai varjostettavalla pinnalla. Varjorelaatioiden laskenta suoritetaan hierarkkisesti, ja tehokasta esitystä varjostavista pinnoista ylläpidetään inkrementaalisesti. Algoritmi on yleiskäyttöinen työkalu näkyvyysrelaatiojoukkojen ratkaisemiseen, ja sillä voi olla muitakin käyttökohteita varjojen laskennan lisäksi. Uuden algoritmin yksityiskohtaisen kuvauksen lisäksi työssä analysoidaan useita olemassa olevia fysikaalisesti oikeiden pehmeiden varjojen laskenta-algoritmeja ja luokitellaan ne algoritmisten kompleksisuusluokkiensa perusteella. Työssä esitetään myös kokeellisia tuloksia, joiden avulla voidaan arvioida algoritmin käyttökelpoisuutta erilaisissa laskentatilanteissa.
  • Modular primitives for high-performance differentiable rendering
    (2020-12) Laine, Samuli; Hellsten, Janne; Karras, Tero; Seol, Yeongho; Lehtinen, Jaakko; Aila, Timo
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    We present a modular differentiable renderer design that yields performance superior to previous methods by leveraging existing, highly optimized hardware graphics pipelines. Our design supports all crucial operations in a modern graphics pipeline: rasterizing large numbers of triangles, attribute interpolation, filtered texture lookups, as well as user-programmable shading and geometry processing, all in high resolutions. Our modular primitives allow custom, high-performance graphics pipelines to be built directly within automatic differentiation frameworks such as PyTorch or TensorFlow. As a motivating application, we formulate facial performance capture as an inverse rendering problem and show that it can be solved efficiently using our tools. Our results indicate that this simple and straightforward approach achieves excellent geometric correspondence between rendered results and reference imagery.
  • Multiresolution terrain rendering and editing
    (2010) Nuuros, Esa
     School of Science | Master's thesis
  • Noise2Noise: Learning image restoration without clean data
    (2018-01-01) Lehtinen, Jaakko; Munkberg, Jacob; Hasselgren, Jon; Laine, Samuli; Karras, Tero; Aittala, Miika; Aila, Timo
     A4 Artikkeli konferenssijulkaisussa
    We apply basic statistical reasoning to signal reconstruction by machine learning - learning to map corrupted observations to clean signals - with a simple and powerful conclusion: It is possible to learn to restore images by only looking at corrupted examples, at performance at and some-times exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denois- ing synthetic Monte Carlo images, and reconstruction of undersampled MRI scans - all corrupted by different processes - based on noisy data only.