Rendering 2019 - DL-only / Industry Track

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632799

Browse

Browsing Rendering 2019 - DL-only / Industry Track by Subject "Computing methodologies"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    Adaptive Multi-view Path Tracing
    (The Eurographics Association, 2019) Fraboni, Basile; Iehl, Jean-Claude; Nivoliers, Vincent; Bouchard, Guillaume; Boubekeur, Tamy and Sen, Pradeep
    Rendering photo-realistic image sequences using path tracing and Monte Carlo integration often requires sampling a large number of paths to get converged results. In the context of rendering multiple views or animated sequences, such sampling can be highly redundant. Several methods have been developed to share sampled paths between spatially or temporarily similar views. However, such sharing is challenging since it can lead to bias in the final images. Our contribution is a Monte Carlo sampling technique which generates paths, taking into account several cameras. First, we sample the scene from all the cameras to generate hit points. Then, an importance sampling technique generates bouncing directions which are shared by a subset of cameras. This set of hit points and bouncing directions is then used within a regular path tracing solution. For animated scenes, paths remain valid for a fixed time only, but sharing can still occur between cameras as long as their exposure time intervals overlap. We show that our technique generates less noise than regular path tracing and does not introduce noticeable bias.
  • Thumbnail Image
    Item
    Foveated Real-Time Path Tracing in Visual-Polar Space
    (The Eurographics Association, 2019) Koskela, Matias; Lotvonen, Atro; Mäkitalo, Markku; Kivi, Petrus; Viitanen, Timo; Jääskeläinen, Pekka; Boubekeur, Tamy and Sen, Pradeep
    Computing power is still the limiting factor in photorealistic real-time rendering. Foveated rendering improves perceived quality by focusing the rendering effort on where the user is looking at. Applying foveated rendering to real-time path tracing where we must work on a very small number of samples per pixel introduces additional challenges; the rendering result is thoroughly noisy and sparse in the periphery. In this paper we demonstrate foveated real-time path tracing system and propose a novel Visual-Polar space in which both real-time path tracing and denoising is done before mapping to screen space. When path tracing a regular grid of samples in Visual-Polar space, the screen space sample distribution follows the human visual acuity model, making both the rendering and denoising 2:5x faster with similar perceived quality. In addition, when using Visual- Polar space, primary rays stay more coherent, leading to improved utilization of the GPU resources and, therefore, making ray traversal 1.3 - 1.5x faster. Moreover, Visual-Polar space improves 1 sample per pixel denoising quality in the fovea. We show that Visual-Polar based path tracing enables real-time rendering for contemporary virtual reality devices even without dedicated ray tracing hardware acceleration.
  • Thumbnail Image
    Item
    Impulse Responses for Precomputing Light from Volumetric Media
    (The Eurographics Association, 2019) Dubouchet, Adrien; Sloan, Peter-Pike; Jarosz, Wojciech; Nowrouzezahrai, Derek; Boubekeur, Tamy and Sen, Pradeep
    Modern interactive rendering can rely heavily on precomputed static lighting on surfaces and in volumes. Scattering from volumetric media can be similarly treated using precomputation, but transport from volumes onto surfaces is typically ignored here. We propose a compact, efficient method to simulate volume-to-surface transport during lighting precomputation . We leverage a novel model of the spherical impulse response of light scattered (and attenuated) in volumetric media to simulate light transport from volumes onto surfaces with simple precomputed lookup tables. These tables model the impulse response as a function of distance and angle to the light and surfaces. We then remap the impulse responses to media with arbitrary, potentially heterogeneous scattering parameters and various phase functions. Moreover, we can compose our impulse response model to treat multiple scattering events in the volume (arriving at surfaces). We apply our method to precomputed volume-to-surface light transport in complex scenes, generating results indistinguishable from ground truth simulations. Our tables allow us to precompute volume-to-surface transport orders of magnitude faster than even an optimized path tracing-based solution would.
  • Thumbnail Image
    Item
    Puppet Dubbing
    (The Eurographics Association, 2019) Fried, Ohad; Agrawala, Maneesh; Boubekeur, Tamy and Sen, Pradeep
    Dubbing puppet videos to make the characters (e.g. Kermit the Frog) convincingly speak a new speech track is a popular activity with many examples of well-known puppets speaking lines from films or singing rap songs. But manually aligning puppet mouth movements to match a new speech track is tedious as each syllable of the speech must match a closed-open-closed segment of mouth movement for the dub to be convincing. In this work, we present two methods to align a new speech track with puppet video, one semi-automatic appearance-based and the other fully-automatic audio-based. The methods offer complementary advantages and disadvantages. Our appearance-based approach directly identifies closed-open-closed segments in the puppet video and is robust to low-quality audio as well as misalignments between the mouth movements and speech in the original performance, but requires some manual annotation. Our audio-based approach assumes the original performance matches a closed-open-closed mouth segment to each syllable of the original speech. It is fully automatic, robust to visual occlusions and fast puppet movements, but does not handle misalignments in the original performance. We compare the methods and show that both improve the credibility of the resulting video over simple baseline techniques, via quantitative evaluation and user ratings.
  • Thumbnail Image
    Item
    Spectral Primary Decomposition for Rendering with sRGB Reflectance
    (The Eurographics Association, 2019) Mallett, Ian; Yuksel, Cem; Boubekeur, Tamy and Sen, Pradeep
    Spectral renderers, as-compared to RGB renderers, are able to simulate light transport that is closer to reality, capturing light behavior that is impossible to simulate with any three-primary decomposition. However, spectral rendering requires spectral scene data (e.g. textures and material properties), which is not widely available, severely limiting the practicality of spectral rendering. Unfortunately, producing a physically valid reflectance spectrum from a given sRGB triple has been a challenging problem, and indeed until very recently constructing a spectrum without colorimetric round-trip error was thought to be impossible. In this paper, we introduce a new procedure for efficiently generating a reflectance spectrum from any given sRGB input data. We show for the first time that it is possible to create any sRGB reflectance spectrum as a linear combination of three separate spectra, each directly corresponding to one of the BT.709 primaries. Our approach produces consistent results, such that the input sRGB value is perfectly reproduced by the corresponding reflectance spectrum under D65 illumination, bounded only by Monte Carlo and numerical error. We provide a complete implementation, including a precomputed spectral basis, and discuss important optimizations and generalization to other RGB spaces.