信息正则化约束反演用于从稀疏监督稳定编辑可编辑的人形化身
Information-Regularized Constrained Inversion for Stable Avatar Editing from Sparse Supervision
AI总结：
本文提出信息正则化约束反演方法，通过在结构化的化身潜在空间中进行约束反演，限制更新到低维的部分特定编辑子空间，以防止身份泄漏和姿态依赖的时序闪烁，提升在稀疏监督下的稳定性。
摘要：
编辑可动的人形化身通常依赖于稀疏监督，通常是几个编辑的关键帧，但简单地将重建的化身拟合到这些编辑经常导致身份泄漏和姿态依赖的时间闪烁。我们主张这些失败最好被理解为一个病态的反演：可用的编辑约束不足以确定负责预期编辑的潜在方向。我们提出了一种条件引导的编辑重建框架，通过在结构化的化身潜在空间中进行约束反演，限制更新到低维的部分特定编辑子空间以防止意外的身份变化。关键的是，我们在反演过程中设计编辑约束，通过优化从完整解码和渲染管道的局部线性化导出的条件目标，得到一个编辑子空间的信息矩阵，其谱预测稳定性和驱动帧重新加权/关键帧激活。所提出的方法在小子空间矩阵上运行，并且可以高效实现（例如，通过Hessian向量积），并在有限编辑监督下提高了稳定性。
英文摘要：
Editing animatable human avatars typically relies on sparse supervision, often a few edited keyframes, yet naively fitting a reconstructed avatar to these edits frequently causes identity leakage and pose-dependent temporal flicker. We argue that these failures are best understood as an ill-conditioned inversion: the available edited constraints do not sufficiently determine the latent directions responsible for the intended edit. We propose a conditioning-guided edited reconstruction framework that performs editing as a constrained inversion in a structured avatar latent space, restricting updates to a low-dimensional, part-specific edit subspace to prevent unintended identity changes. Crucially, we design the editing constraints during inversion by optimizing a conditioning objective derived from a local linearization of the full decoding-and-rendering pipeline, yielding an edit-subspace information matrix whose spectrum predicts stability and drives frame reweighting / keyframe activation. The resulting method operates on small subspace matrices and can be implemented efficiently (e.g., via Hessian-vector products), and improves stability under limited edited supervision.
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。
