IEEE transactions on visualization and computer graphics最新文献

We propose Transmission-Reflection Gaussians (TRGaussians), a novel 3D-Gaussian-based representation for highfidelity rendering of planar transmission and reflection, which are ubiquitous in indoor scenes. Our method combines 3D Gaussians with learnable reflection planes that explicitly model the glass planes with view-dependent reflectance strengths. Real scenes and transmission components are modeled by 3D Gaussians and the reflection components are modeled by the mirrored Gaussians with respect to the reflection plane. The transmission and reflection components are blended according to a Fresnelbased, view-dependent weighting scheme, allowing for faithful synthesis of complex appearance effects under varying viewpoints. To effectively optimize TR-Gaussians, we develop a multistage optimization framework incorporating color and geometry constraints and an opacity perturbation mechanism. Experiments on different datasets demonstrate that TR-Gaussians achieve real-time, high-fidelity novel view synthesis in scenes with planar transmission and reflection, and outperform state-of-the-art approaches both quantitatively and qualitatively.

Design spaces serve as conceptual frameworks that enable systematic exploration of possibilities and constraints for particular design problems. Despite growing recognition of their importance in visualization research, the community faces two main challenges: characterizing what constitute a design space, given the lack of consensus on its definition, and determining how to construct these spaces in the absence of established methodologies. To address the challenges, we first conducted a literature review of visualization design space research, identifying three distinct research threads. Focusing on the thread that views design spaces as multi-dimensional frameworks, we refined our corpus to 49 papers and developed a unified conceptualization of design spaces. Building on this foundation, we proposed a systematic approach to design space construction, synthesized from an analysis of practices spanning five phases: exploration, data collection, creation, evaluation, and communication.

Vection, the visual illusion of self-motion, provides a strong marker of the VR user experience and plays an important role in both presence and cybersickness. Traditional measurements have been conducted using questionnaires, which exhibit inherent limitations due to their subjective nature and prevent real-time adjustments. Detecting vection in real time would allow VR systems to adapt to users' needs, improving comfort and minimizing negative effects like cybersickness. This paper investigates the presence of vection markers in electroencephalographic (EEG) brain signals using evoked potentials (brain responses to external stimuli). We designed a VR experiment that induces vection using two conditions: (1) forward acceleration or (2) backward acceleration. We recorded electroencephalographic (EEG) signals and gathered subjective reports on thirty (30) participants. We found an evoked potential of vection characterized by a positive peak around 600 ms (P600) after stimulus onset in the parietal region and a simultaneous negative peak in the frontal region. This result paves the way for the automatic detection of vection using EEG as well as a better understanding of vection. It also provides insights into the functional role of the visual system and its integration with the vestibular system during motion-perception. It has the potential to help enhance VR user experience by qualifying users' perceived vection and adapting the VR environments accordingly.

3D Gaussian Splatting has demonstrated remarkable real-time rendering capabilities and superior visual quality in novel view synthesis for static scenes. Building upon these advantages, researchers have progressively extended 3D Gaussians to dynamic scene reconstruction. Deformation field-based methods have emerged as a promising approach among various techniques. These methods maintain 3D Gaussian attributes in a canonical field and employ the deformation field to transform this field across temporal sequences. Nevertheless, these approaches frequently encounter challenges such as suboptimal rendering speeds, significant dependence on initial point clouds, and vulnerability to local optima in dim scenes. To overcome these limitations, we present FRoG, an efficient and robust framework for high-quality dynamic scene reconstruction. FRoG integrates per-Gaussian embedding with a coarse-to-fine temporal embedding strategy, accelerating rendering through the early fusion of temporal embeddings. Moreover, to enhance robustness against sparse initializations, we introduce a novel depth- and error-guided sampling strategy. This strategy populates the canonical field with new 3D Gaussians at low-deviation initial positions, significantly reducing the optimization burden on the deformation field and improving detail reconstruction in both static and dynamic regions. Furthermore, by modulating opacity variations, we mitigate the local optima problem in dim scenes, improving color fidelity. Comprehensive experimental results validate that our method achieves accelerated rendering speeds while maintaining state-of-the-art visual quality.

Existing learning-based visual retouching primarily focuses on improving image quality through end-to-end objective mapping between input and retouched images. However, these approaches often overlook two critical aspects: the progressive nature of image retouching and the subjective aesthetic preferences, resulting in suboptimal visual outcomes. To address this, we introduce Automatic Aesthetic Image Retouching via active reinforcement learning (A $^{3}$ RL) to enhance the visualization experience in two sub-tasks: color enhancement and composition optimization, which are formulated as a unified Markov Decision Process in the proposed A $^{3}$ RL framework. In our approach, each pixel functions as an autonomous agent that determines optimal actions based on aesthetic guidance, engaging in online exploration through immediate pixel-wise and channel-wise feedback from the aesthetic environment. By leveraging a pretrained image aesthetic model, our method ensures that the A $^{3}$ RL process aligns with human aesthetic preferences and adheres to subjective aesthetic principles. The framework integrates pixel-level retouching actions with image-level operations to achieve optimal image sequences through progressive iterations. Extensive experiments demonstrate that our method effectively recalibrates image aesthetics across multiple dimensions: low-level quality metrics (PSNR, SSIM), visual perception (LPIPS), and subjective visual experience (human survey). The results demonstrate high consistency with expert-retouched ground-truth images. Source code is available at: https://github.com/S-Ir-V/color_crop.

The present study suggests that the bar-tip limit error-assuming the raw data are limited by the bar-tip-assessed with one question, moderates the within-the-bar bias-rating values inside the bar as more likely than those outside the bar-and that this bias is resilient to reduction through explanation.

Although significant progress has been made in the field of speech-driven 3D facial animation recently, the speech-driven animation of an indispensable facial component, eye gaze, has been overlooked by recent research. This is primarily due to the weak correlation between speech and eye gaze, as well as the scarcity of audio-gaze data, making it very challenging to generate 3D eye gaze motion from speech alone. In this paper, we propose a novel data-driven method which can generate diverse 3D eye gaze motions in harmony with the speech. To achieve this, we firstly construct an audio-gaze dataset that contains about 14 hours of audio-mesh sequences featuring high-quality eye gaze motion, head motion and facial motion simultaneously. The motion data is acquired by performing lightweight eye gaze fitting and face reconstruction on videos from existing audio-visual datasets. We then tailor a novel speech-to-motion translation framework in which the head motions and eye gaze motions are jointly generated from speech but are modeled in two separate latent spaces. This design stems from the physiological knowledge that the rotation range of eyeballs is less than that of head. Through mapping the speech embedding into the two latent spaces, the difficulty in modeling the weak correlation between speech and non-verbal motion is thus attenuated. Finally, our TalkingEyes, integrated with a speech-driven 3D facial motion generator, can synthesize eye gaze motion, eye blinks, head motion and facial motion collectively from speech. Qualitative and quantitative evaluations, along with a perceptual user study, demonstrate the superiority of the proposed method in generating diverse and natural 3D eye gaze motions from speech. The project page of this paper is: https://lkjkjoiuiu.github.io/TalkingEyes_Home/.

We present DIQ-MPM, a novel monolithic two-way coupling framework for simulating interactions between solids modeled with the total Lagrangian formulation and Eulerian incompressible fluids using the Material Point Method (MPM). Our approach combines an implicit TLMPM formulation with a mixed velocity-pressure scheme to robustly simulate compressible solids undergoing large deformations, while eliminating numerical fractures. To enable strong fluid-solid coupling without relying on overlapping grids, we introduce a Dual Interface Quadrature (DIQ) mechanism that maps fluid-solid interface information consistently between the current and reference configurations. This allows us to construct a unified sparse pressure-only system via Schur complement, leading to efficient and stable coupling. We also integrate a particle-based contact force model to resolve solid-solid and solid-boundary contacts within implicit TLMPM. Experimental results demonstrate that our method stably captures free-slip coupling, large deformation phenomena, and complex interactions between compressible solids and incompressible fluids.

Text-guided texture generation has been rapidly developed with the proliferation of generative artificial intelligence for creating three-dimensional textured objects. However, existing text-guided texture generation methods often suffer from artifacts such as inconsistent visual appearance across different views, the Janus problems and seams in texture maps. To address these issues, we propose a novel text-guided texture generation method, named WonderTex. It achieves the generation of high-quality, view-consistent, and seamless texture maps through a two-stage pipeline. Specifically, we fine-tune a Stable Diffusion model using a large dataset to obtain a multi-view image diffusion model capable of generating a 4-view grid. This model serves as the foundation for producing four consistent views and establishing the base texture in the first stage. Subsequently, an automatic view selection and inpainting strategy is employed to effectively f ill and refine the texture maps in the second stage. Extensive experiments have shown that our method is effective and robust, capable of generating high-quality textures with various meshes and prompts, outperforming baseline methods in terms of texture details, view consistency, and other metrics.

We introduce a novel approach to simulate the interaction between fluids and thin elastic solids without any penetration. Our approach is centered around an optimization system augmented with barriers, which aims to find a configuration that ensures the absence of penetration while enforcing incompressibility for the fluids and minimizing elastic potentials for the solids. Unlike previous methods that primarily focus on velocity coherence at the fluid-solid interfaces, we demonstrate the effectiveness and flexibility of explicitly resolving positional constraints, including both explicit representation of solid positions and the implicit representation of fluid level-set interface. To preserve the volume of the fluid, we propose a simple yet efficient approach that adjusts the associated level-set values. Additionally, we develop a distance metric capable of measuring the separation between an implicitly represented surface and a Lagrangian object of arbitrary codimension. By integrating the inertia, solid elastic potential, damping, barrier potential, and fluid incompressibility within a unified system, we are able to robustly simulate a wide range of processes involving fluid interactions with lower-dimensional objects such as shells and rods. These processes include topology changes, bouncing, splashing, sliding, rolling, floating, and more.