2023-04-07 更新
DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models
Authors:Yukang Cao, Yan-Pei Cao, Kai Han, Ying Shan, Kwan-Yee K. Wong
We present DreamAvatar, a text-and-shape guided framework for generating high-quality 3D human avatars with controllable poses. While encouraging results have been produced by recent methods on text-guided 3D common object generation, generating high-quality human avatars remains an open challenge due to the complexity of the human body’s shape, pose, and appearance. We propose DreamAvatar to tackle this challenge, which utilizes a trainable NeRF for predicting density and color features for 3D points and a pre-trained text-to-image diffusion model for providing 2D self-supervision. Specifically, we leverage SMPL models to provide rough pose and shape guidance for the generation. We introduce a dual space design that comprises a canonical space and an observation space, which are related by a learnable deformation field through the NeRF, allowing for the transfer of well-optimized texture and geometry from the canonical space to the target posed avatar. Additionally, we exploit a normal-consistency regularization to allow for more vivid generation with detailed geometry and texture. Through extensive evaluations, we demonstrate that DreamAvatar significantly outperforms existing methods, establishing a new state-of-the-art for text-and-shape guided 3D human generation.
PDF 19 pages, 19 figures. Project page: https://yukangcao.github.io/DreamAvatar/
点此查看论文截图
Image Stabilization for Hololens Camera in Remote Collaboration
Authors:Gowtham Senthil, Siva Vignesh Krishnan, Annamalai Lakshmanan, Florence Kissling
With the advent of new technologies, Augmented Reality (AR) has become an effective tool in remote collaboration. Narrow field-of-view (FoV) and motion blur can offer an unpleasant experience with limited cognition for remote viewers of AR headsets. In this article, we propose a two-stage pipeline to tackle this issue and ensure a stable viewing experience with a larger FoV. The solution involves an offline 3D reconstruction of the indoor environment, followed by enhanced rendering using only the live poses of AR device. We experiment with and evaluate the two different 3D reconstruction methods, RGB-D geometric approach and Neural Radiance Fields (NeRF), based on their data requirements, reconstruction quality, rendering, and training times. The generated sequences from these methods had smoother transitions and provided a better perspective of the environment. The geometry-based enhanced FoV method had better renderings as it lacked blurry outputs making it better than the other attempted approaches. Structural Similarity Index (SSIM) and Peak Signal to Noise Ratio (PSNR) metrics were used to quantitatively show that the rendering quality using the geometry-based enhanced FoV method is better. Link to the code repository - https://github.com/MixedRealityETHZ/ImageStabilization.
PDF
点此查看论文截图
DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Model
Authors:Hoigi Seo, Hayeon Kim, Gwanghyun Kim, Se Young Chun
The increasing demand for high-quality 3D content creation has motivated the development of automated methods for creating 3D object models from a single image and/or from a text prompt. However, the reconstructed 3D objects using state-of-the-art image-to-3D methods still exhibit low correspondence to the given image and low multi-view consistency. Recent state-of-the-art text-to-3D methods are also limited, yielding 3D samples with low diversity per prompt with long synthesis time. To address these challenges, we propose DITTO-NeRF, a novel pipeline to generate a high-quality 3D NeRF model from a text prompt or a single image. Our DITTO-NeRF consists of constructing high-quality partial 3D object for limited in-boundary (IB) angles using the given or text-generated 2D image from the frontal view and then iteratively reconstructing the remaining 3D NeRF using inpainting latent diffusion model. We propose progressive 3D object reconstruction schemes in terms of scales (low to high resolution), angles (IB angles initially to outer-boundary (OB) later), and masks (object to background boundary) in our DITTO-NeRF so that high-quality information on IB can be propagated into OB. Our DITTO-NeRF outperforms state-of-the-art methods in terms of fidelity and diversity qualitatively and quantitatively with much faster training times than prior arts on image/text-to-3D such as DreamFusion, and NeuralLift-360.
PDF Project page: https://janeyeon.github.io/ditto-nerf/
点此查看论文截图
LANe: Lighting-Aware Neural Fields for Compositional Scene Synthesis
Authors:Akshay Krishnan, Amit Raj, Xianling Zhang, Alexandra Carlson, Nathan Tseng, Sandhya Sridhar, Nikita Jaipuria, James Hays
Neural fields have recently enjoyed great success in representing and rendering 3D scenes. However, most state-of-the-art implicit representations model static or dynamic scenes as a whole, with minor variations. Existing work on learning disentangled world and object neural fields do not consider the problem of composing objects into different world neural fields in a lighting-aware manner. We present Lighting-Aware Neural Field (LANe) for the compositional synthesis of driving scenes in a physically consistent manner. Specifically, we learn a scene representation that disentangles the static background and transient elements into a world-NeRF and class-specific object-NeRFs to allow compositional synthesis of multiple objects in the scene. Furthermore, we explicitly designed both the world and object models to handle lighting variation, which allows us to compose objects into scenes with spatially varying lighting. This is achieved by constructing a light field of the scene and using it in conjunction with a learned shader to modulate the appearance of the object NeRFs. We demonstrate the performance of our model on a synthetic dataset of diverse lighting conditions rendered with the CARLA simulator, as well as a novel real-world dataset of cars collected at different times of the day. Our approach shows that it outperforms state-of-the-art compositional scene synthesis on the challenging dataset setup, via composing object-NeRFs learned from one scene into an entirely different scene whilst still respecting the lighting variations in the novel scene. For more results, please visit our project website https://lane-composition.github.io/.
PDF Project website: https://lane-composition.github.io
点此查看论文截图