Search Results

Volumetric modeling and neural radiance field representations have revolutionized 3D face capture and photorealistic novel view synthesis. However, these methods often require hundreds of multi-view input images and are thus inapplicable to cases with ...

High-fidelity digital human representations are increasingly in demand in the digital world, particularly for interactive telepresence, AR/VR, 3D graphics, and the rapidly evolving metaverse. Even though they work well in small spaces, ...

• Generates high-quality, animatable human avatars from single-camera video in minutes.
• Pre-trained model: Enhances human estimation in dynamic NeRF for better avatars.
• Efficient rendering: Replaces standard NeRF with a SoTA model ...

We present a versatile NeRF-based simulator for testing autonomous driving (AD) software systems, designed with a focus on sensor-realistic closed-loop evaluation and the creation of safety-critical scenarios. The simulator learns from sequences ...

3D Gaussian splatting, emerging as a groundbreaking approach, has drawn increasing attention for its capabilities of high-fidelity reconstruction and real-time rendering. However, it couples the appearance and geometry of the scene within the ...

Generalizability and few-shot learning are key challenges in Neural Radiance Fields (NeRF), often due to the lack of a holistic understanding in pixel-level rendering. We introduce CaesarNeRF, an end-to-end approach that leverages scene-level CA...

In this paper, we introduce the Volumetric Relightable Morphable Model (VRMM), a novel volumetric and parametric facial prior for 3D face modeling. While recent volumetric prior models offer improvements over traditional methods like 3D Morphable Models (...

In the area of neural rendering-based novel view synthesis, illumination is important since shadows cast by objects under various light sources provide indications about their geometries and materials. However, due to high physical device ...

3D facial reconstruction is essential for metaverse applications. Traditional mesh-based methods have difficulty rendering photorealistic faces and complex objects. Recent advancements in Neural Radiance Fields (NeRFs) have excelled in ...

Display Omitted

• A novel network, EMOVA, which uses two emotional stimuli from images and the corresponding voice to learn subtle differences in facial expression.
• The attention-based fusion method to efficiently combine the information of images and ...

Recent breakthroughs in neural radiance fields have significantly advanced the field of novel view synthesis and 3D reconstruction from multi-view images. However, the prevalent neural volume rendering techniques often suffer from long rendering ...

• Proposing a novel octree-based method to reconstruct implicit surfaces from multi-view images.
• Enabling real-time rendering while maintaining reconstruction quality comparable to existing techniques.
• Enabling converting slow-...

In order to realize the digital management and manufacturing of air material, the methods of 3D point cloud enhancement optimization and high-fidelity texture reconstruction in entity digitization of air material based on the fusion of 3D ...

This paper presents a simple yet practical network architecture, ProLiF (Progressively-connected Light Field network), for the efficient differentiable view synthesis of complex forward-facing scenes in both the training and inference stages. The ...

Display Omitted

• Introduction of ProLiF, a simple and efficient network architecture for differentiable view synthesis.
• Development of a progressive training strategy with novel regularization losses to ensure multi-view 3D consistency.
• ...

The Neural Radiance Field (NeRF) exhibits excellent performance for view synthesis tasks, but it requires a large amount of memory and model parameters during three-dimensional (3D) scene reconstruction. This paper proposes a block-term tensor ...

Data augmentation has contributed to the rapid advancement of unsupervised learning on 3D point clouds. However, we argue that data augmentation is not ideal, as it requires a careful application-dependent selection of the types of augmentations ...

Existing real-time RGB-D reconstruction approaches, like Kinect Fusion, lack real-time photo-realistic visualization. This is due to noisy, oversmoothed or incomplete geometry and blurry textures which are fused from imperfect depth maps and camera ...

In this paper, we propose a novel framework, Tracking-free Relightable Avatar (TRAvatar), for capturing and reconstructing high-fidelity 3D avatars. Compared to previous methods, TRAvatar works in a more practical and efficient setting. Specifically, ...

Mobile cameras have revolutionized content creation, allowing casual users to capture professional-looking photos. However, capturing the perfect moment can still be challenging, making post-capture editing desirable. In this work, we introduce ExShot, ...

Synthesis of new views in dynamic 3D scenes is a challenging task in 3D vision. However, most current approaches rely on radiance fields built upon multi-view camera systems for dynamic scenes, which are expensive and time-consuming, and depend ...

Display Omitted

• We proposed a model to represent dynamic scenes, which achieved high rendering quality on both synthetic and real datasets.
• We applied a special tensor decomposition technique to accelerate the training process and reduce the space ...

Previewing the shaded output of 3D models has been a long-standing requirement in the field. Typically, this is achieved by applying common materials; however, this approach is often labor-intensive and can yield only rough results in the trial ...

Display Omitted

• Rendering 2D images from 3D face meshes with a single 2D reference image.
• Geometry and appearance disentanglement through mesh explicit representation.
• Injecting 3D information into the StyleGAN2 generator for superior geometry ...

This paper presents a novel approach for text/speech-driven animation of a photo-realistic head model based on blend-shape geometry, dynamic textures, and neural rendering. Training a VAE for geometry and texture yields a parametric ...

Display Omitted

This article presents object-oriented neural light transfer (NeLT), a novel neural representation of the dynamic light transportation between an object and the environment. Our method disentangles the global illumination of a scene into individual objects’...