用于单目视频动态人体重建的时间残差神经辐射场
Temporal Residual Neural Radiance Fields for Monocular Video Dynamic Human Body Reconstruction
浏览论文内容
中文总结 AI 辅助
本文针对MLP用于动态人体重建的局限，提出时间残差神经辐射场方法，构建时间残差场、优化效率并设计多维损失，在保持Anim-NeRF等精度的同时，将时间效率提升近780倍。
中文摘要 AI 辅助
在计算机视觉与图形学领域，近年已有多种方法通过单个多层感知器（MLP）实现了静态场景中人体的高质量重建。然而，MLP存在容量限制，用于动态场景重建时需要大量训练时间与计算资源，且重建质量受到显著制约。本文提出一种有效处理动态场景人体三维建模中复杂时空信号的方法，采用时间残差神经辐射场（Temporal Residual Neural Radiance Fields）实现人体的新视图渲染与新姿态合成。为解决视频序列中时间信号的表示问题，本文构建了与MLP架构无关的时间残差场；其次，为提升重建效率，提出一种集成方法，减少可训练参数并加速渲染，从而增强网络的特征表示能力；最后，设计了多维损失函数以准确测量预测与实际空间像素值间的损失。实验结果表明，与最新代表性方法相比，本文方法提升了峰值信噪比（PSNR）与结构相似性指数（SSIM）精度指标，在保持与Anim-NeRF、Neural Body相近精度的同时，实现了近780倍的时间效率提升。
英文摘要
In the field of computer vision and graphics, high-quality reconstruction of the human body in static scenes has been achieved in recent years by a single multilayer perceptron (MLP) in a number of approaches. However, MLPs have capacity limitations, requiring substantial training time and computational resources for dynamic scene reconstruction. And the quality of reconstruction is significantly constrained. This paper proposes a method for effectively processing complex spatiotemporal signals in dynamic scene human 3D modeling. The proposed method uses Temporal Residual Neural Radiance Fields to achieve novel view rendering and new pose synthesis of human bodies.To address the problem of representing temporal signals in video sequences, we construct a temporal residual field which is not related to the MLP architecture. Secondly, to improve reconstruction efficiency, we propose an integrated approach that reduces trainable parameters and accelerates rendering, thereby enhancing the network's feature representation capability. Finally, we design a multi-dimensional loss function to accurately measure the loss between predicted and actual spatial pixel values. The experimental results show that our proposed approach improves the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) accuracy metrics compared to the latest representative methods. It maintains similar accuracy to Anim-NeRF and Neural Body while achieving a nearly 780-fold increase in time efficiency.
发表机构
- Nanchang University（南昌大学）
机构由 AI 辅助整理，请以论文原文为准。
