Proceedings of the ACM on Computer Graphics and Interactive Techniques: Vol. 3, No. 1. 2020

Full Citation in the ACM Digital Library

A Three-Level Approach to Texture Mapping and Synthesis on 3D Surfaces

We present a method for example-based texturing of triangular 3D meshes. Our algorithm maps a small 2D texture sample onto objects of arbitrary size in a seamless fashion, with no visible repetitions and low overall distortion. It requires minimal user interaction and can be applied to complex, multi-layered input materials that are not required to be tileable. Our framework integrates a patch-based approach with per-pixel compositing. To minimize visual artifacts, we run a three-level optimization that starts with a rigid alignment of texture patches (macro scale), then continues with non-rigid adjustments (meso scale) and finally performs pixel-level texture blending (micro scale). We demonstrate that the relevance of the three levels depends on the texture content and type (stochastic, structured, or anisotropic textures).

Lossy Geometry Compression for High Resolution Voxel Scenes

Sparse Voxel Directed Acyclic Graphs (SVDAGs) losslessly compress highly detailed geometry in a high-resolution binary voxel grid by identifying matching elements. This representation is suitable for high-performance real-time applications, such as free-viewpoint videos and high-resolution precomputed shadows. In this work, we introduce a lossy scheme to further decrease memory consumption by minimally modifying the underlying voxel grid to increase matches. Our method efficiently identifies groups of similar but rare subtrees in an SVDAG structure and replaces them with a single common subtree representative. We test our compression strategy on several standard voxel datasets, where we obtain memory reductions of 10% up to 50% compared to a standard SVDAG, while introducing an error (ratio of modified voxels to voxel count) of only 1% to 5%. Furthermore, we show that our method is complementary to other state of the art SVDAG optimizations, and has a negligible effect on real-time rendering performance.

Real-time subsurface scattering with single pass variance-guided adaptive importance sampling

In real-time applications, it is difficult to simulate realistic subsurface scattering with differing degrees translucency. Burley's reflectance approximation by empirically fitting the diffusion profile as a whole makes it possible to achieve realistic looking subsurface scattering for different translucent materials in screen space. However, achieving a physically correct result requires real-time Monte Carlo sampling of the analytic importance function per pixel per frame, which seems prohibitive to achieve. In this paper, we propose an approximation of the importance function that can be evaluated in real-time. Since subsurface scattering is more pronounced in certain regions (e.g., with light gradient change), we propose an adaptive sampling method based on temporal variance to lower the required number of samples. We propose a one phase adaptive sampling pass that is unbiased, and able to adapt to scene changes due to motion and lighting. To further improve the quality, we explore temporal reuse with a guiding pass prior to the final temporal anti-aliasing (TAA) phase that further improves the quality. Our local guiding pass does not constrain the TAA implementation, and only requires one additional texture to be passed between frames. Our proposed variance-guided algorithm has the potential to make stochastic sampling algorithm effective for real-time rendering.

Real-time Approximation of Photometric Polygonal Lights

We present a real-time rendering technique for photometric polygonal lights. Our method uses a numerical integration technique based on a triangulation to calculate noise-free diffuse shading. We include a dynamic point in the triangulation that provides a continuous near-field illumination resembling the shape of the light emitter and its characteristics. We evaluate the accuracy of our approach with a diverse selection of photometric measurement data sets in a comprehensive benchmark framework. Furthermore, we provide an extension for specular reflection on surfaces with arbitrary roughness that facilitates the use of existing real-time shading techniques. Our technique is easy to integrate into real-time rendering systems and extends the range of possible applications with photometric area lights.

Real-Time Stochastic Lightcuts

We present real-time stochastic lightcuts, a real-time rendering method for scenes with many dynamic lights. Our method is the GPU extension of stochastic lightcuts [Yuksel 2019], a state-of-art hierarchical light sampling algorithm for offline rendering. To support arbitrary dynamic scenes, we introduce an extremely fast light tree builder. To maximize the performance of light sampling on the GPU, we introduce cut sharing, a way to reuse adaptive sampling information in light trees in neighboring pixels.

Image-Based Rendering of Cars using Semantic Labels and Approximate Reflection Flow

Image-Based Rendering (IBR) has made impressive progress towards highly realistic, interactive 3D navigation for many scenes, including cityscapes. However, cars are ubiquitous in such scenes; multi-view stereo reconstruction provides proxy geometry for IBR, but has difficulty with shiny car bodies, and leaves holes in place of reflective, semi-transparent windows on cars. We present a new approach allowing free-viewpoint IBR of cars based on an approximate analytic reflection flow computation on curved windows. Our method has three components: a refinement step of reconstructed car geometry guided by semantic labels, that provides an initial approximation for missing window surfaces and a smooth completed car hull; an efficient reflection flow computation using an ellipsoid approximation of the curved car windows that runs in real-time in a shader and a reflection/background layer synthesis solution. These components allow plausible rendering of reflective, semi-transparent windows in free viewpoint navigation. We show results on several scenes casually captured with a single consumer-level camera, demonstrating plausible car renderings with significant improvement in visual quality over previous methods.

Passthrough+: Real-time Stereoscopic View Synthesis for Mobile Mixed Reality

We present an end-to-end system for real-time environment capture, 3D reconstruction, and stereoscopic view synthesis on a mobile VR headset. Our solution allows the user to use the cameras on their VR headset as their eyes to see and interact with the real world while still wearing their headset, a feature often referred to as Passthrough. The central challenge when building such a system is the choice and implementation of algorithms under the strict compute, power, and performance constraints imposed by the target user experience and mobile platform. A key contribution of this paper is a complete description of a corresponding system that performs temporally stable passthrough rendering at 72 Hz with only 200 mW power consumption on a mobile Snapdragon 835 platform. Our algorithmic contributions for enabling this performance include the computation of a coarse 3D scene proxy on the embedded video encoding hardware, followed by a depth densification and filtering step, and finally stereoscopic texturing and spatio-temporal up-sampling. We provide a detailed discussion and evaluation of the challenges we encountered, as well as algorithm and performance trade-offs in terms of compute and resulting passthrough quality.;AB@The described system is available to users as the Passthrough+ feature on Oculus Quest. We believe that by publishing the underlying system and methods, we provide valuable insights to the community on how to design and implement real-time environment sensing and rendering on heavily resource constrained hardware.

Local Optimization for Robust Signed Distance Field Collision

Signed distance fields (SDFs) are a popular shape representation for collision detection. This is due to their query efficiency, and the ability to provide robust inside/outside information. Although it is straightforward to test points for interpenetration with an SDF, it is not clear how to extend this to continuous surfaces, such as triangle meshes. In this paper, we propose a per-element local optimization to find the closest points between the SDF isosurface and mesh elements. This allows us to generate accurate contact points between sharp point-face pairs, and handle smoothly varying edge-edge contact. We compare three numerical methods for solving the local optimization problem: projected gradient descent, Frank-Wolfe, and golden-section search. Finally, we demonstrate the applicability of our method to a wide range of scenarios including collision of simulated cloth, rigid bodies, and deformable solids.

A Time-independent Deformer for Elastic-rigid Contacts

We introduce a new tool that assists artists in deforming an elastic object when it comes in intersection with a rigid one. As opposed to methods that rely on time-resolved simulations, our approach is entirely based on time-independent geometric operators. It thus restarts from scratch at every frame from a pair of objects in intersection and works in two stages: the intersected regions are first matched and a contact region is identified on the rigid object; the elastic object is then deformed to match the contact while producing plausible bulge effects with controllable volume preservation. Our direct deformation approach brings several advantages to 3D animators: it provides instant feedback, permits non-linear editing, allows for the replicability of the deformation in different settings, and grants control over exaggerated or stylized bulging effects.