可重光照的全息人物：从稀疏视角捕捉并重光照动态人体表演
Relightable Holoported Characters: Capturing and Relighting Dynamic Human Performance from Sparse Views
用粗人体网格代理上的 texel 对齐 3D 高斯泼溅作为可重光照表示，并用 Transformer 单次前向隐式求解渲染方程，可迁移到稀疏视角动态人体重建与任意光照下的新视角合成。
原文依据 regresses the relit appearance in the form of texel-aligned 3D Gaussian splats attached to the coarse mesh proxy
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出可重光照的全息人物（Relightable Holoported Characters, RHC），一种新颖的特定人物方法，仅需推理时由稀疏视角 RGB 视频观测，即可实现全身且高度动态的人体的自由视角渲染与重光照。与经典的一次一盏灯（OLAT）人体重光照不同，我们基于 Transformer 的 RelightNet 在单次网络前向中预测重光照外观，避免了昂贵的 OLAT 基采集与生成。为训练该模型，我们引入一种新的采集策略与数据集，在多视角灯光舞台中录制，其中由随机环境贴图照明的帧与均匀照明的跟踪帧交替出现，从而同时实现精确的运动跟踪以及多样的光照与动态覆盖。受渲染方程启发，我们从粗人体网格代理与输入视角中导出物理信息特征，编码几何、反照率、着色与虚拟相机视角。随后 RelightNet 以这些特征为输入，将其与一种新颖的光照条件进行交叉注意力，并以附着于粗网格代理的 texel 对齐 3D 高斯泼溅形式回归重光照外观。因此，RelightNet 隐式地学会在单次前馈中高效地为新光照条件计算渲染方程。实验表明，与最优方法相比，我们的方法具有更优的视觉保真度与光照复现能力。
英文原文摘要 1447 字符
We present _Relightable Holoported Characters_ (RHC), a novel person-specific method for free-view rendering and relighting of full-body and highly dynamic humans solely observed from sparse-view RGB videos at inference. In contrast to classical one-light-at-a-time (OLAT)-based human relighting, our transformer-based RelightNet predicts relit appearance within a single network pass, avoiding costly OLAT-basis capture and generation. For training such a model, we introduce a new capture strategy and dataset recorded in a multi-view lightstage, where we alternate frames lit by random environment maps with uniformly lit tracking frames, simultaneously enabling accurate motion tracking and diverse illumination as well as dynamics coverage. Inspired by the rendering equation, we derive physics-informed features that encode geometry, albedo, shading, and the virtual camera view from a coarse human mesh proxy and the input views. Our RelightNet then takes these features as input and cross-attends them with a novel lighting condition, and regresses the relit appearance in the form of texel-aligned 3D Gaussian splats attached to the coarse mesh proxy. Consequently, our RelightNet implicitly learns to efficiently compute the rendering equation for novel lighting conditions within a single feed-forward pass. Experiments demonstrate our method's superior visual fidelity and lighting reproduction compared to state-of-the-art approaches.