The diffusion model has long been plagued by scalability and quadratic
complexity issues, especially within transformer-based structures. In this
study, we aim to leverage the long sequence modeling capability of a
State-Space Model called Mamba to extend its applicability to visual data
generation. Firstly, we identify a critical oversight in most current
Mamba-based vision methods, namely the lack of consideration for spatial
continuity in the scan scheme of Mamba. Secondly, building upon this insight,
we introduce a simple, plug-and-play, zero-parameter method named Zigzag Mamba,
which outperforms Mamba-based baselines and demonstrates improved speed and
memory utilization compared to transformer-based baselines. Lastly, we
integrate Zigzag Mamba with the Stochastic Interpolant framework to investigate
the scalability of the model on large-resolution visual datasets, such as
FacesHQ $1024\times 1024$ and UCF101, MultiModal-CelebA-HQ, and MS COCO
$256\times 256$. Code will be released at this https URL

应用 Mamba 的 State-Space 模型，通过引入一种名为 Zigzag Mamba 的方法来解决视觉数据生成中的缺陷，提升了速度和内存利用率，并将其与 Stochastic Interpolant 框架相结合以研究模型在大分辨率视觉数据集上的可扩展性。

ZigMa: 蜿蜒进化扩散模型

ZigMa: Zigzag Mamba Diffusion Model

We present \emph{SPHEAR}, an accurate, differentiable parametric statistical
3D human head model, enabled by a novel 3D registration method based on
spherical embeddings. We shift the paradigm away from the classical Non-Rigid
Registration methods, which operate under various surface priors, increasing
reconstruction fidelity and minimizing required human intervention.
Additionally, SPHEAR is a \emph{complete} model that allows not only to sample
diverse synthetic head shapes and facial expressions, but also gaze directions,
high-resolution color textures, surface normal maps, and hair cuts represented
in detail, as strands. SPHEAR can be used for automatic realistic visual data
generation, semantic annotation, and general reconstruction tasks. Compared to
state-of-the-art approaches, our components are fast and memory efficient, and
experiments support the validity of our design choices and the accuracy of
registration, reconstruction and generation techniques.

我们提出了一种准确、可微分的参数化统计 3D 人头模型 SPHEAR，通过基于球形嵌入的新型 3D 注册方法实现。SPHEAR 不仅可以采样不同的合成头部形状和面部表情，还可以表示凝视方向、高分辨率彩色纹理、表面法线图和具体的发型切割，可用于自动逼真的视觉数据生成、语义注释和通用重建任务，与最先进的方法相比，我们的组件快速且存储效率高，实验证明了我们设计选择的合理性以及注册、重建和生成技术的准确性。