DSpace Repository

Search Results

Now showing 1 - 10 of 13

MesoGAN: Generative Neural Reflectance Shells
(© 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2023) Diolatzis, Stavros; Novak, Jan; Rousselle, Fabrice; Granskog, Jonathan; Aittala, Miika; Ramamoorthi, Ravi; Drettakis, George; Hauser, Helwig and Alliez, Pierre
We introduce MesoGAN, a model for generative 3D neural textures. This new graphics primitive represents mesoscale appearance by combining the strengths of generative adversarial networks (StyleGAN) and volumetric neural field rendering. The primitive can be applied to surfaces as a neural reflectance shell; a thin volumetric layer above the surface with appearance parameters defined by a neural network. To construct the neural shell, we first generate a 2D feature texture using StyleGAN with carefully randomized Fourier features to support arbitrarily sized textures without repeating artefacts. We augment the 2D feature texture with a learned height feature, which aids the neural field renderer in producing volumetric parameters from the 2D texture. To facilitate filtering, and to enable end‐to‐end training within memory constraints of current hardware, we utilize a hierarchical texturing approach and train our model on multi‐scale synthetic datasets of 3D mesoscale structures. We propose one possible approach for conditioning MesoGAN on artistic parameters (e.g. fibre length, density of strands, lighting direction) and demonstrate and discuss integration into physically based renderers.
Point-Based Neural Rendering with Per-View Optimization
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Kopanas, Georgios; Philip, Julien; Leimkühler, Thomas; Drettakis, George; Bousseau, Adrien and McGuire, Morgan
There has recently been great interest in neural rendering methods. Some approaches use 3D geometry reconstructed with Multi-View Stereo (MVS) but cannot recover from the errors of this process, while others directly learn a volumetric neural representation, but suffer from expensive training and inference. We introduce a general approach that is initialized with MVS, but allows further optimization of scene properties in the space of input views, including depth and reprojected features, resulting in improved novel-view synthesis. A key element of our approach is our new differentiable point-based pipeline, based on bi-directional Elliptical Weighted Average splatting, a probabilistic depth test and effective camera selection. We use these elements together in our neural renderer, that outperforms all previous methods both in quality and speed in almost all scenes we tested. Our pipeline can be applied to multi-view harmonization and stylization in addition to novel-view synthesis.
Video-Based Rendering of Dynamic Stationary Environments from Unsynchronized Inputs
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Thonat, Theo; Aksoy, Yagiz; Aittala, Miika; Paris, Sylvain; Durand, Fredo; Drettakis, George; Bousseau, Adrien and McGuire, Morgan
Image-Based Rendering allows users to easily capture a scene using a single camera and then navigate freely with realistic results. However, the resulting renderings are completely static, and dynamic effects - such as fire, waterfalls or small waves - cannot be reproduced. We tackle the challenging problem of enabling free-viewpoint navigation including such stationary dynamic effects, but still maintaining the simplicity of casual capture. Using a single camera - instead of previous complex synchronized multi-camera setups - means that we have unsynchronized videos of the dynamic effect from multiple views, making it hard to blend them when synthesizing novel views. We present a solution that allows smooth free-viewpoint video-based rendering (VBR) of such scenes using temporal Laplacian pyramid decomposition video, enabling spatio-temporal blending. For effects such as fire and waterfalls, that are semi-transparent and occupy 3D space, we first estimate their spatial volume. This allows us to create per-video geometries and alpha-matte videos that we can blend using our frequency-dependent method. We also extend Laplacian blending to the temporal dimension to remove additional temporal seams. We show results on scenes containing fire, waterfalls or rippling waves at the seaside, bringing these scenes to life.
Guided Fine-Tuning for Large-Scale Material Transfer
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Deschaintre, Valentin; Drettakis, George; Bousseau, Adrien; Dachsbacher, Carsten and Pharr, Matt
We present a method to transfer the appearance of one or a few exemplar SVBRDFs to a target image representing similar materials. Our solution is extremely simple: we fine-tune a deep appearance-capture network on the provided exemplars, such that it learns to extract similar SVBRDF values from the target image. We introduce two novel material capture and design workflows that demonstrate the strength of this simple approach. Our first workflow allows to produce plausible SVBRDFs of large-scale objects from only a few pictures. Specifically, users only need take a single picture of a large surface and a few close-up flash pictures of some of its details.We use existing methods to extract SVBRDF parameters from the close-ups, and our method to transfer these parameters to the entire surface, enabling the lightweight capture of surfaces several meters wide such as murals, floors and furniture. In our second workflow, we provide a powerful way for users to create large SVBRDFs from internet pictures by transferring the appearance of existing, pre-designed SVBRDFs. By selecting different exemplars, users can control the materials assigned to the target image, greatly enhancing the creative possibilities offered by deep appearance capture.
Practical Product Path Guiding Using Linearly Transformed Cosines
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Diolatzis, Stavros; Gruson, Adrien; Jakob, Wenzel; Nowrouzezahrai, Derek; Drettakis, George; Dachsbacher, Carsten and Pharr, Matt
Path tracing is now the standard method used to generate realistic imagery in many domains, e.g., film, special effects, architecture etc. Path guiding has recently emerged as a powerful strategy to counter the notoriously long computation times required to render such images. We present a practical path guiding algorithm that performs product sampling, i.e., samples proportional to the product of the bidirectional scattering distribution function (BSDF) and incoming radiance. We use a spatial-directional subdivision to represent incoming radiance, and introduce the use of Linearly Transformed Cosines (LTCs) to represent the BSDF during path guiding, thus enabling efficient product sampling. Despite the computational efficiency of LTCs, several optimizations are needed to make our method cost effective. In particular, we show how we can use vectorization, precomputation, as well as strategies to optimize multiple importance sampling and Russian roulette to improve performance. We evaluate our method on several scenes, demonstrating consistent improvement in efficiency compared to previous work, especially in scenes with significant glossy inter-reflection.
ModalNeRF: Neural Modal Analysis and Synthesis for Free-Viewpoint Navigation in Dynamically Vibrating Scenes
(The Eurographics Association and John Wiley & Sons Ltd., 2023) Petitjean, Automne; Poirier-Ginter, Yohan; Tewari, Ayush; Cordonnier, Guillaume; Drettakis, George; Ritschel, Tobias; Weidlich, Andrea
Recent advances in Neural Radiance Fields enable the capture of scenes with motion. However, editing the motion is hard; no existing method allows editing beyond the space of motion existing in the original video, nor editing based on physics. We present the first approach that allows physically-based editing of motion in a scene captured with a single hand-held video camera, containing vibrating or periodic motion. We first introduce a Lagrangian representation, representing motion as the displacement of particles, which is learned while training a radiance field. We use these particles to create a continuous representation of motion over the sequence, which is then used to perform a modal analysis of the motion thanks to a Fourier transform on the particle displacement over time. The resulting extracted modes allow motion synthesis, and easy editing of the motion, while inheriting the ability for free-viewpoint synthesis in the captured 3D scene from the radiance field.We demonstrate our new method on synthetic and real captured scenes.
Neural Precomputed Radiance Transfer
(The Eurographics Association and John Wiley & Sons Ltd., 2022) Rainer, Gilles; Bousseau, Adrien; Ritschel, Tobias; Drettakis, George; Chaine, Raphaëlle; Kim, Min H.
Recent advances in neural rendering indicate immense promise for architectures that learn light transport, allowing efficient rendering of global illumination effects once such methods are trained. The training phase of these methods can be seen as a form of pre-computation, which has a long standing history in Computer Graphics. In particular, Pre-computed Radiance Transfer (PRT) achieves real-time rendering by freezing some variables of the scene (geometry, materials) and encoding the distribution of others, allowing interactive rendering at runtime. We adopt the same configuration as PRT - global illumination of static scenes under dynamic environment lighting - and investigate different neural network architectures, inspired by the design principles and theoretical analysis of PRT. We introduce four different architectures, and show that those based on knowledge of light transport models and PRT-inspired principles improve the quality of global illumination predictions at equal training time and network size, without the need for high-end ray-tracing hardware.
Improving NeRF Quality by Progressive Camera Placement for Free-Viewpoint Navigation
(The Eurographics Association, 2023) Kopanas, Georgios; Drettakis, George; Guthe, Michael; Grosch, Thorsten
Neural Radiance Fields, or NeRFs, have drastically improved novel view synthesis and 3D reconstruction for rendering. NeRFs achieve impressive results on object-centric reconstructions, but the quality of novel view synthesis with free-viewpoint navigation in complex environments (rooms, houses, etc) is often problematic. While algorithmic improvements play an important role in the resulting quality of novel view synthesis, in this work, we show that because optimizing a NeRF is inherently a data-driven process, good quality data play a fundamental role in the final quality of the reconstruction. As a consequence, it is critical to choose the data samples - in this case the cameras - in a way that will eventually allow the optimization to converge to a solution that allows free-viewpoint navigation with good quality. Our main contribution is an algorithm that efficiently proposes new camera placements that improve visual quality with minimal assumptions. Our solution can be used with any NeRF model and outperforms baselines and similar work.
Physically-Based Lighting for 3D Generative Models of Cars
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Violante, Nicolas; Gauthier, Alban; Diolatzis, Stavros; Leimkühler, Thomas; Drettakis, George; Bermano, Amit H.; Kalogerakis, Evangelos
Recent work has demonstrated that Generative Adversarial Networks (GANs) can be trained to generate 3D content from 2D image collections, by synthesizing features for neural radiance field rendering. However, most such solutions generate radiance, with lighting entangled with materials. This results in unrealistic appearance, since lighting cannot be changed and view-dependent effects such as reflections do not move correctly with the viewpoint. In addition, many methods have difficulty for full, 360? rotations, since they are often designed for mainly front-facing scenes such as faces. We introduce a new 3D GAN framework that addresses these shortcomings, allowing multi-view coherent 360? viewing and at the same time relighting for objects with shiny reflections, which we exemplify using a car dataset. The success of our solution stems from three main contributions. First, we estimate initial camera poses for a dataset of car images, and then learn to refine the distribution of camera parameters while training the GAN. Second, we propose an efficient Image-Based Lighting model, that we use in a 3D GAN to generate disentangled reflectance, as opposed to the radiance synthesized in most previous work. The material is used for physically-based rendering with a dataset of environment maps. Third, we improve the 3D GAN architecture compared to previous work and design a careful training strategy that allows effective disentanglement. Our model is the first that generate a variety of 3D cars that are multi-view consistent and that can be relit interactively with any environment map.
A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis
(The Eurographics Association and John Wiley & Sons Ltd., 2024) Poirier-Ginter, Yohan; Gauthier, Alban; Philip, Julien; Lalonde, Jean-François; Drettakis, George; Garces, Elena; Haines, Eric
Relighting radiance fields is severely underconstrained for multi-view data, which is most often captured under a single illumination condition; It is especially hard for full scenes containing multiple objects. We introduce a method to create relightable radiance fields using such single-illumination data by exploiting priors extracted from 2D image diffusion models. We first fine-tune a 2D diffusion model on a multi-illumination dataset conditioned by light direction, allowing us to augment a single-illumination capture into a realistic - but possibly inconsistent - multi-illumination dataset from directly defined light directions. We use this augmented data to create a relightable radiance field represented by 3D Gaussian splats. To allow direct control of light direction for low-frequency lighting, we represent appearance with a multi-layer perceptron parameterized on light direction. To enforce multi-view consistency and overcome inaccuracies we optimize a per-image auxiliary feature vector. We show results on synthetic and real multi-view data under single illumination, demonstrating that our method successfully exploits 2D diffusion model priors to allow realistic 3D relighting for complete scenes.

Filters

Author

Subject

Date

Has files

Settings

Sort By

Results per page

Search Results