Computer Graphics Forum最新文献

Monte Carlo rendering of translucent objects with heterogeneous scattering properties is often expensive both in terms of memory and computation. If the scattering properties are described by a 3D texture, memory consumption is high. If we do path tracing and use a high dynamic range lighting environment, the computational cost of the rendering can easily become significant. We propose a compact and efficient neural method for representing and rendering the appearance of heterogeneous translucent objects. Instead of assuming only surface variation of optical properties, our method represents the appearance of a full object taking its geometry and volumetric heterogeneities into account. This is similar to a neural radiance field, but our representation works for an arbitrary distant lighting environment. In a sense, we present a version of neural precomputed radiance transfer that captures relighting of heterogeneous translucent objects. We use a multi-layer perceptron (MLP) with skip connections to represent the appearance of an object as a function of spatial position, direction of observation, and direction of incidence. The latter is considered a directional light incident across the entire non-self-shadowed part of the object. We demonstrate the ability of our method to compactly store highly complex materials while having high accuracy when comparing to reference images of the represented object in unseen lighting environments. As compared with path tracing of a heterogeneous light scattering volume behind a refractive interface, our method more easily enables importance sampling of the directions of incidence and can be integrated into existing rendering frameworks while achieving interactive frame rates.

While the past of terrain cannot be known precisely because an effect can result from many different causes, exploring these possible pasts opens the way to numerous applications ranging from movies and games to paleogeography. We introduce unerosion, an attempt to recover plausible past topographies from an input terrain represented as a height field. Our solution relies on novel algorithms for the backward simulation of different processes: fluvial erosion, sedimentation, and thermal erosion. This is achieved by re-formulating the equations of erosion and sedimentation so that they can be simulated back in time. These algorithms can be combined to account for a succession of climate changes backward in time, while the possible ambiguities provide editing options to the user. Results show that our solution can approximately reverse different types of erosion while enabling users to explore a variety of alternative pasts. Using a chronology of climatic periods to inform us about the main erosion phenomena, we also went back in time using real measured terrain data. We checked the consistency with geological findings, namely the height of river beds hundreds of thousands of years ago.

While IMU based motion capture offers a cost-effective alternative to premium camera-based systems, it often falls short in matching the latter's realism. Common distortions, such as self-penetrating body parts, foot skating, and floating, limit the usability of these systems, particularly for high-end users. To address this, we employed reinforcement learning to train an AI agent that mimics erroneous sample motion. Since our agent operates within a simulated environment, it inherently avoids generating these distortions since it must adhere to the laws of physics. Impressively, the agent manages to mimic the sample motions while preserving their distinctive characteristics. We assessed our method's efficacy across various types of input data, showcasing an ideal blend of artefact-laden IMU-based data with high-grade optical motion capture data. Furthermore, we compared the configuration of observation and action spaces with other implementations, pinpointing the most suitable configuration for our purposes. All our models underwent rigorous evaluation using a spectrum of quantitative metrics complemented by a qualitative review. These evaluations were performed using a benchmark dataset of IMU-based motion data from actors not included in the training data.

Co-speech gesturing is an important modality in conversation, providing context and social cues. In character animation, appropriate and synchronised gestures add realism, and can make interactive agents more engaging. Historically, methods for automatically generating gestures were predominantly audio-driven, exploiting the prosodic and speech-related content that is encoded in the audio signal. In this paper we instead experiment with using Large-Language Model (LLM) features for gesture generation that are extracted from text using Llama2. We compare against audio features, and explore combining the two modalities in both objective tests and a user study. Surprisingly, our results show that Llama2 features on their own perform significantly better than audio features and that including both modalities yields no significant difference to using Llama2 features in isolation. We demonstrate that the Llama2 based model can generate both beat and semantic gestures without any audio input, suggesting LLMs can provide rich encodings that are well suited for gesture generation.

Traditional mesh-based methods for cutting deformable bodies rely on modifying the simulation mesh by deleting, duplicating, deforming or subdividing its elements. Unfortunately, such topological changes eventually lead to instability, reduced accuracy, or computational efficiency challenges. Hence, state of the art algorithms favor the extended finite element method (XFEM), which decouples the cut geometry from the simulation mesh, allowing for stable and accurate cuts at an additional computational cost that is local to the cut region. However, in the 3-dimensional setting, current XFEM frameworks are limited by the cutting configurations that they support. In particular, intersecting cuts are either prohibited or require sophisticated special treatment. Our work presents a general XFEM formulation that is applicable to the 1-, 2-, and 3-dimensional setting without sacrificing the desirable properties of the method. In particular, we propose a generalized enrichment which supports multiple intersecting cuts of various degrees of non-linearity by leveraging recent advances in robust mesh-Boolean technology. This novel strategy additionally enables analytic discontinuous integration schemes required to compute mass, force and elastic energy. We highlight the simplicity, expressivity and accuracy of our XFEM implementation across various scenarios in which intersecting cutting patterns are featured.

We present a novel multi-layer method for extended position-based dynamics that exploits a sequence of reduced models consisting of rigid and elastic parts to speed up convergence. Taking inspiration from concepts like adaptive rigidification and long-range constraints, we automatically generate different rigid bodies at each layer based on the current strain rate. During the solve, the rigid bodies provide coupling between progressively less distant vertices during layer iterations, and therefore the fully elastic iterations at the final layer start from a lower residual error. Our layered approach likewise helps with the treatment of contact, where the mixed solves of both rigid and elastic in the layers permit fast propagation of impacts. We show several experiments that guide the selection of parameters of the solver, including the number of layers, the iterations per layers, as well as the choice of rigid patterns. Overall, our results show lower compute times for achieving a desired residual reduction across a variety of simulation models and scenarios.