WildRayZer：动态环境中自监督的大视角合成

摘要

我们提出WildRayZer——一种用于动态环境（相机与物体皆可移动）中新颖视角合成的自监督框架。动态内容会破坏静态NVS模型所依赖的多视角一致性，导致重影、虚幻几何和不稳定的姿态估计。WildRayZer通过执行分析-合成测试解决此问题：仅考虑相机运动的静态渲染器解析刚性结构，其残差则揭示瞬变区域。基于这些残差，我们构建伪运动掩码、蒸馏出运动估计器，并利用其掩码输入令牌及门控损失梯度，使监督聚焦于跨视角背景补全。为实现大规模训练与评估，我们构建了Dynamic RealEstate10K（D-RE10K）——包含1.5万段随意拍摄动态序列的真实数据集，以及配对的瞬变/干净基准D-RE10K-iPhone，用于稀疏视角的瞬变感知NVS。实验表明，WildRayZer在单次前向传播中，无论是瞬变区域消除还是全帧NVS质量，均持续优于基于优化的前馈基线方法。

English

We present WildRayZer, a self-supervised framework for novel view synthesis (NVS) in dynamic environments where both the camera and objects move. Dynamic content breaks the multi-view consistency that static NVS models rely on, leading to ghosting, hallucinated geometry, and unstable pose estimation. WildRayZer addresses this by performing an analysis-by-synthesis test: a camera-only static renderer explains rigid structure, and its residuals reveal transient regions. From these residuals, we construct pseudo motion masks, distill a motion estimator, and use it to mask input tokens and gate loss gradients so supervision focuses on cross-view background completion. To enable large-scale training and evaluation, we curate Dynamic RealEstate10K (D-RE10K), a real-world dataset of 15K casually captured dynamic sequences, and D-RE10K-iPhone, a paired transient and clean benchmark for sparse-view transient-aware NVS. Experiments show that WildRayZer consistently outperforms optimization-based and feed-forward baselines in both transient-region removal and full-frame NVS quality with a single feed-forward pass.

WildRayZer：动态环境中自监督的大视角合成

WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments

摘要

Support