Splannequin：基於雙重檢測濺射的單目人體模型挑戰影像凍結技術

摘要

從單目人體模型挑戰（MC）影片中合成高保真度的凍結3D場景，是一個有別於標準動態場景重建的獨特問題。我們的目標並非著重於運動建模，而是創建凍結場景的同時策略性保留細微動態，以實現用戶可控的瞬時選擇。為此，我們提出動態高斯潑濺技術的新穎應用：通過動態建模場景來保留鄰近時間域的變化，並透過固定模型的時間參數來渲染靜態場景。然而在此應用下，單目捕捉與稀疏時間監督會導致高斯元素在弱監督時間點出現未被觀測或遮擋的偽影（如重影與模糊）。我們提出Splannequin——一種與架構無關的正則化方法，可檢測高斯圖元的兩種狀態（隱藏狀態與缺陷狀態）並實施時間錨定。在主要為前向相機運動的條件下，隱藏狀態會錨定於近期被充分觀測的過去狀態，而缺陷狀態則錨定於具有更強監督訊號的未來狀態。本方法透過簡潔的損失項即可整合至現有動態高斯流程，無需調整架構且不增加推理負載，顯著提升視覺品質，實現了用戶可選擇凍結時間的高保真渲染，並獲得96%用戶偏好度的實證。項目頁面：https://chien90190.github.io/splannequin/

English

Synthesizing high-fidelity frozen 3D scenes from monocular Mannequin-Challenge (MC) videos is a unique problem distinct from standard dynamic scene reconstruction. Instead of focusing on modeling motion, our goal is to create a frozen scene while strategically preserving subtle dynamics to enable user-controlled instant selection. To achieve this, we introduce a novel application of dynamic Gaussian splatting: the scene is modeled dynamically, which retains nearby temporal variation, and a static scene is rendered by fixing the model's time parameter. However, under this usage, monocular capture with sparse temporal supervision introduces artifacts like ghosting and blur for Gaussians that become unobserved or occluded at weakly supervised timestamps. We propose Splannequin, an architecture-agnostic regularization that detects two states of Gaussian primitives, hidden and defective, and applies temporal anchoring. Under predominantly forward camera motion, hidden states are anchored to their recent well-observed past states, while defective states are anchored to future states with stronger supervision. Our method integrates into existing dynamic Gaussian pipelines via simple loss terms, requires no architectural changes, and adds zero inference overhead. This results in markedly improved visual quality, enabling high-fidelity, user-selectable frozen-time renderings, validated by a 96% user preference. Project page: https://chien90190.github.io/splannequin/

Splannequin：基於雙重檢測濺射的單目人體模型挑戰影像凍結技術

Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting

摘要

Support