153 results
Search Results
Now showing 1 - 10 of 153
Item Edge-Friend: Fast and Deterministic Catmull-Clark Subdivision Surfaces(The Eurographics Association and John Wiley & Sons Ltd., 2023) Kuth, Bastian; Oberberger, Max; Chajdas, Matthäus; Meyer, Quirin; Bikker, Jacco; Gribble, ChristiaanWe present edge-friend, a data structure for quad meshes with access to neighborhood information required for Catmull-Clark subdivision surface refinement. Edge-friend enables efficient real-time subdivision surface rendering. In particular, the resulting algorithm is deterministic, does not require hardware support for atomic floating-point arithmetic, and is optimized for efficient rendering on GPUs. Edge-friend exploits that after one subdivision step, two edges can be uniquely and implicitly assigned to each quad. Additionally, edge-friend is a compact data structure, adding little overhead. Our algorithm is simple to implement in a single compute shader kernel, and requires minimal synchronization which makes it particularly suited for asynchronous execution. We easily extend our kernel to support relevant Catmull-Clark subdivision surface features, including semi-smooth creases, boundaries, animation and attribute interpolation. In case of topology changes, our data structure requires little preprocessing, making it amendable for a variety of applications, including real-time editing and animations. Our method can process and render billions of triangles per second on modern GPUs. For a sample mesh, our algorithm generates and renders 2.9 million triangles in 0.58ms on an AMD Radeon RX 7900 XTX GPU.Item Towards a Neural Graphics Pipeline for Controllable Image Generation(The Eurographics Association and John Wiley & Sons Ltd., 2021) Chen, Xuelin; Cohen-Or, Daniel; Chen, Baoquan; Mitra, Niloy J.; Mitra, Niloy and Viola, IvanIn this paper, we leverage advances in neural networks towards forming a neural rendering for controllable image generation, and thereby bypassing the need for detailed modeling in conventional graphics pipeline. To this end, we present Neural Graphics Pipeline (NGP), a hybrid generative model that brings together neural and traditional image formation models. NGP decomposes the image into a set of interpretable appearance feature maps, uncovering direct control handles for controllable image generation. To form an image, NGP generates coarse 3D models that are fed into neural rendering modules to produce view-specific interpretable 2D maps, which are then composited into the final output image using a traditional image formation model. Our approach offers control over image generation by providing direct handles controlling illumination and camera parameters, in addition to control over shape and appearance variations. The key challenge is to learn these controls through unsupervised training that links generated coarse 3D models with unpaired real images via neural and traditional (e.g., Blinn- Phong) rendering functions, without establishing an explicit correspondence between them. We demonstrate the effectiveness of our approach on controllable image generation of single-object scenes. We evaluate our hybrid modeling framework, compare with neural-only generation methods (namely, DCGAN, LSGAN, WGAN-GP, VON, and SRNs), report improvement in FID scores against real images, and demonstrate that NGP supports direct controls common in traditional forward rendering. Code is available at http://geometry.cs.ucl.ac.uk/projects/2021/ngp.Item Dense 3D Gaussian Splatting Initialization for Sparse Image Data(The Eurographics Association, 2024) Seibt, Simon; Chang, Thomas Vincent Siu-Lung; von Rymon Lipinski, Bartosz ; Latoschik, Marc Erich; Liu, Lingjie; Averkiou, MelinosThis paper presents advancements in novel-view synthesis with 3D Gaussian Splatting (3DGS) using a dense and accurate SfM point cloud initialization approach. We address the challenge of achieving photorealistic renderings from sparse image data, where basic 3DGS training may result in suboptimal convergence, thus leading to visual artifacts. The proposed method enhances precision and density of initially reconstructed point clouds by refining 3D positions and extrapolating additional points, even for difficult image regions, e.g. with repeating patterns and suboptimal visual coverage. Our contributions focus on improving ''Dense Feature Matching for Structure-from-Motion'' (DFM4SfM) based on a homographic decomposition of the image space to support 3DGS training: First, a grid-based feature detection method is introduced for DFM4SfM to ensure a welldistributed 3D Gaussian initialization uniformly over all depth planes. Second, the SfM feature matching is complemented by a geometric plausibility check, priming the homography estimation and thereby improving the initial placement of 3D Gaussians. Experimental results on the NeRF-LLFF dataset demonstrate that this approach achieves superior qualitative and quantitative results, even for fewer views, and the potential for a significantly accelerated 3DGS training with faster convergence.Item Single-Image SVBRDF Estimation with Learned Gradient Descent(The Eurographics Association and John Wiley & Sons Ltd., 2024) Luo, Xuejiao; Scandolo, Leonardo; Bousseau, Adrien; Eisemann, Elmar; Bermano, Amit H.; Kalogerakis, EvangelosRecovering spatially-varying materials from a single photograph of a surface is inherently ill-posed, making the direct application of a gradient descent on the reflectance parameters prone to poor minima. Recent methods leverage deep learning either by directly regressing reflectance parameters using feed-forward neural networks or by learning a latent space of SVBRDFs using encoder-decoder or generative adversarial networks followed by a gradient-based optimization in latent space. The former is fast but does not account for the likelihood of the prediction, i.e., how well the resulting reflectance explains the input image. The latter provides a strong prior on the space of spatially-varying materials, but this prior can hinder the reconstruction of images that are too different from the training data. Our method combines the strengths of both approaches. We optimize reflectance parameters to best reconstruct the input image using a recurrent neural network, which iteratively predicts how to update the reflectance parameters given the gradient of the reconstruction likelihood. By combining a learned prior with a likelihood measure, our approach provides a maximum a posteriori estimate of the SVBRDF. Our evaluation shows that this learned gradient-descent method achieves state-of-the-art performance for SVBRDF estimation on synthetic and real images.Item Video-Driven Animation of Neural Head Avatars(The Eurographics Association, 2023) Paier, Wolfgang; Hinzer, Paul; Hilsmann, Anna; Eisert, Peter; Guthe, Michael; Grosch, ThorstenWe present a new approach for video-driven animation of high-quality neural 3D head models, addressing the challenge of person-independent animation from video input. Typically, high-quality generative models are learned for specific individuals from multi-view video footage, resulting in person-specific latent representations that drive the generation process. In order to achieve person-independent animation from video input, we introduce an LSTM-based animation network capable of translating person-independent expression features into personalized animation parameters of person-specific 3D head models. Our approach combines the advantages of personalized head models (high quality and realism) with the convenience of video-driven animation employing multi-person facial performance capture.We demonstrate the effectiveness of our approach on synthesized animations with high quality based on different source videos as well as an ablation study.Item Art-directing Appearance using an Environment Map Latent Space(The Eurographics Association, 2021) Petikam, Lohit; Chalmers, Andrew; Anjyo, Ken; Rhee, Taehyun; Lee, Sung-Hee and Zollmann, Stefanie and Okabe, Makoto and Wünsche, BurkhardIn look development, environment maps (EMs) are used to verify 3D appearance in varied lighting (e.g., overcast, sunny, and indoor). Artists can only assign one fixed material, making it laborious to edit appearance uniquely for all EMs. Artists can artdirect material and lighting in film post-production. However, this is impossible in dynamic real-time games and live augmented reality (AR), where environment lighting is unpredictable. We present a new workflow to customize appearance variation across a wide range of EM lighting, for live applications. Appearance edits can be predefined, and then automatically adapted to environment lighting changes. We achieve this by learning a novel 2D latent space of varied EM lighting. The latent space lets artists browse EMs in a semantically meaningful 2D view. For different EMs, artists can paint different material and lighting parameter values directly on the latent space. We robustly encode new EMs into the same space, for automatic look-up of the desired appearance. This solves a new problem of preserving art-direction in live applications, without any artist intervention.Item World-Space Spatiotemporal Path Resampling for Path Tracing(The Eurographics Association and John Wiley & Sons Ltd., 2023) Zhang, Hangyu; Wang, Beibei; Chaine, Raphaëlle; Deng, Zhigang; Kim, Min H.With the advent of hardware-accelerated ray tracing, more and more real-time rendering applications tend to render images with ray-traced global illumination (GI). However, the low sample counts at real-time framerates bring enormous challenges to existing path sampling methods. Recent work (ReSTIR GI) samples indirect illumination effectively with a dramatic bias reduction. However, as a screen-space based path resampling approach, it can only reuse the path at the first bounce and brings subtle benefits for complex scenes. To this end, we propose a world-space based spatiotemporal path resampling approach. Our approach caches more path samples into a world-space grid, which allows reusing sub-path starting from non-primary path vertices. Furthermore, we introduce a practical normal-aware hash grid construction approach, providing more efficient candidate samples for path resampling. Eventually, our method achieves improvements ranging from 16.6% to 41.9% in terms of mean squared errors (MSE) compared against the previous method with only 4.4% ~ 8.4% extra time cost.Item Minimal Convolutional Neural Networks for Temporal Anti Aliasing(The Eurographics Association, 2023) Herveau, Killian; Piochowiak, Max; Dachsbacher, Carsten; Bikker, Jacco; Gribble, ChristiaanExisting deep learning methods for performing temporal anti aliasing (TAA) in rendering are either closed source or rely on upsampling networks with a large operation count which are expensive to evaluate. We propose a simple deep learning architecture for TAA combining only a few common primitives, easy to assemble and to change for application needs. We use a fully-convolutional neural network architecture with recurrent temporal feedback, motion vectors and depth values as input and show that a simple network can produce satisfactory results. Our architecture template, for which we provide code, introduces a method that adapts to different temporal subpixel offsets for accumulation without increasing the operation count. To this end, convolutional layers cycle through a set of different weights per temporal subpixel offset while their operations remain fixed. We analyze the effect of this method on image quality and present different tradeoffs for adapting the architecture. We show that our simple network performs remarkably better than variance clipping TAA, eliminating both flickering and ghosting without performing upsampling.Item Moving Basis Decomposition for Precomputed Light Transport(The Eurographics Association and John Wiley & Sons Ltd., 2021) Silvennoinen, Ari; Sloan, Peter-Pike; Bousseau, Adrien and McGuire, MorganWe study the problem of efficient representation of potentially high-dimensional, spatially coherent signals in the context of precomputed light transport. We present a basis decomposition framework, Moving Basis Decomposition (MBD), that generalizes many existing basis expansion methods and enables high-performance, seamless reconstruction of compressed data. We develop an algorithm for solving large-scale MBD problems. We evaluate MBD against state-of-the-art in a series of controlled experiments and describe a real-world application, where MBD serves as the backbone of a scalable global illumination system powering multiple, current and upcoming 60Hz AAA-titles running on a wide range of hardware platforms.Item Spectral Upsampling Approaches for RGB Illumination(The Eurographics Association, 2022) Guarnera, Giuseppe Claudio; Gitlina, Yuliya; Deschaintre, Valentin; Ghosh, Abhijeet; Ghosh, Abhijeet; Wei, Li-YiWe present two practical approaches for high fidelity spectral upsampling of previously recorded RGB illumination in the form of an image-based representation such as an RGB light probe. Unlike previous approaches that require multiple measurements with a spectrometer or a reference color chart under a target illumination environment, our method requires no additional information for the spectral upsampling step. Instead, we construct a data-driven basis of spectral distributions for incident illumination from a set of six RGBW LEDs (three narrowband and three broadband) that we employ to represent a given RGB color using a convex combination of the six basis spectra. We propose two different approaches for estimating the weights of the convex combination using – (a) genetic algorithm, and (b) neural networks. We additionally propose a theoretical basis consisting of a set of narrow and broad Gaussians as a generalization of the approach, and also evaluate an alternate LED basis for spectral upsampling. We achieve good qualitative matches of the predicted illumination spectrum using our spectral upsampling approach to ground truth illumination spectrum while achieving near perfect matching of the RGB color of the given illumination in the vast majority of cases. We demonstrate that the spectrally upsampled RGB illumination can be employed for various applications including improved lighting reproduction as well as more accurate spectral rendering.