ProxyImg: 通过分层解耦代理嵌入实现高度可控的图像表示
ProxyImg: Towards Highly-Controllable Image Representation via Hierarchical Disentangled Proxy Embedding
AI总结：
ProxyImg通过分层解耦代理嵌入实现高度可控的图像表示，支持高效、细粒度的图像和视频编辑与实时物理动画。
摘要：
现有的图像表示方法，包括显式表示如位图和高斯素量，以及隐式表示如潜在图像，要么存在表示冗余导致手动编辑努力繁重，要么缺乏从潜在变量到语义实例或部分的直接映射，使细粒度操控困难。这些限制阻碍了高效可控的图像和视频编辑。为了解决这些问题，我们提出了一个分层代理参数化的图像表示方法，将语义、几何和纹理属性解耦到独立且可操控的参数空间中。基于对输入图像的语义感知分解，我们的表示通过自适应贝塞尔拟合和迭代内部区域细分和建模来构建分层代理几何。多尺度隐式纹理参数被嵌入到最终的几何感知分布式代理节点中，使在像素域内实现连续高保真重建，并支持实例或部分独立的语义编辑。此外，我们引入了一种局部适应性特征索引机制，以确保空间纹理一致性，进一步支持高质量背景补全而无需依赖生成模型。在图像重建和编辑基准测试，包括ImageNet、OIR-Bench和HumanEdit上进行了广泛的实验，证明我们的方法在参数更少的情况下实现了最先进的渲染保真度，同时实现了直观、交互式和物理合理的操控。此外，通过将代理节点与基于位置的动力学相结合，我们的框架支持使用轻量隐式渲染的实时物理驱动动画，相较于生成方法，在时间一致性和视觉真实感方面均表现更优。
英文摘要：
Prevailing image representation methods, including explicit representations such as raster images and Gaussian primitives, as well as implicit representations such as latent images, either suffer from representation redundancy that leads to heavy manual editing effort, or lack a direct mapping from latent variables to semantic instances or parts, making fine-grained manipulation difficult. These limitations hinder efficient and controllable image and video editing. To address these issues, we propose a hierarchical proxy-based parametric image representation that disentangles semantic, geometric, and textural attributes into independent and manipulable parameter spaces. Based on a semantic-aware decomposition of the input image, our representation constructs hierarchical proxy geometries through adaptive Bezier fitting and iterative internal region subdivision and meshing. Multi-scale implicit texture parameters are embedded into the resulting geometry-aware distributed proxy nodes, enabling continuous high-fidelity reconstruction in the pixel domain and instance- or part-independent semantic editing. In addition, we introduce a locality-adaptive feature indexing mechanism to ensure spatial texture coherence, which further supports high-quality background completion without relying on generative models. Extensive experiments on image reconstruction and editing benchmarks, including ImageNet, OIR-Bench, and HumanEdit, demonstrate that our method achieves state-of-the-art rendering fidelity with significantly fewer parameters, while enabling intuitive, interactive, and physically plausible manipulation. Moreover, by integrating proxy nodes with Position-Based Dynamics, our framework supports real-time physics-driven animation using lightweight implicit rendering, achieving superior temporal consistency and visual realism compared with generative approaches.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
