用神经梯度变形法实现单目视频中动态服装的高精度重建
NGD: Neural Gradient Based Deformation for Monocular Garment Reconstruction
- 基于神经梯度的变形机制，避免传统顶点位移带来的伪影
- 自适应重网格策略有效捕捉裙褶与皱纹等高频细节
- 可学习动态纹理图，还原每帧光照与阴影变化，适合影视特效应用
从单目视频中动态重建服装是一项重要但极具挑战的任务，因其服装的复杂运动特性与非约束形态。尽管神经渲染技术已实现高质量几何重建，但隐式表示方法常因体素渲染导致表面平滑，难以捕捉高频细节；而显式模板方法依赖顶点位移进行形变，易产生伪影。为此，本文提出NGD（Neural Gradient-based Deformation）方法，从单目视频中重建动态纹理服装。同时，设计了一种新型自适应重网格策略，用于建模如裙褶、折痕等随时间演变的表面结构，显著提升重建质量。此外，通过学习每帧动态纹理图，准确捕捉光照与阴影变化。我们在多个方面进行了充分的定性与定量评估，结果表明该方法在视觉效果与指标上均优于现有最先进方法。
原文摘要 · Abstract (English)
Dynamic garment reconstruction from monocular video is an important yet challenging task due to the complex dynamics and unconstrained nature of the garments. Recent advancements in neural rendering have enabled high-quality geometric reconstruction with image/video supervision. However, implicit representation methods that use volume rendering often provide smooth geometry and fail to model high-frequency details. While template reconstruction methods model explicit geometry, they use vertex displacement for deformation, which results in artifacts. Addressing these limitations, we propose NGD, a Neural Gradient-based Deformation method to reconstruct dynamically evolving textured garments from monocular videos. Additionally, we propose a novel adaptive remeshing strategy for modelling dynamically evolving surfaces like wrinkles and pleats of the skirt, leading to high-quality reconstruction. Finally, we learn dynamic texture maps to capture per-frame lighting and shadow effects. We provide extensive qualitative and quantitative evaluations to demonstrate significant improvements over existing SOTA methods and provide high-quality garment reconstructions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。