High-quality novel view synthesis (NVS) from real-world videos is crucial for applications such as cultural heritage preservation, digital twins, and immersive media. However, real-world videos typically contain long sequences with irregular camera trajectories and unknown poses, leading to pose drift, feature misalignment, and geometric distortion during reconstruction. Moreover, lossy compression amplifies these issues by introducing inconsistencies that gradually degrade geometry and rendering quality. While recent studies have addressed either long-sequence NVS or unposed reconstruction, compression-aware approaches still focus on specific artifacts or limited scenarios, leaving diverse compression patterns in long videos insufficiently explored. In this paper, we propose CompSplat, a compression-aware training framework that explicitly models frame-wise compression characteristics to mitigate inter-frame inconsistency and accumulated geometric errors. CompSplat incorporates compression-aware frame weighting and an adaptive pruning strategy to enhance robustness and geometric consistency, particularly under heavy compression. Extensive experiments on challenging benchmarks, including Tanks and Temples, Free, and Hike, demonstrate that CompSplat achieves state-of-the-art rendering quality and pose accuracy, significantly surpassing most recent state-of-the-art NVS approaches under severe compression conditions.

翻译：从真实世界视频中实现高质量的新视角合成对于文化遗产保护、数字孪生和沉浸式媒体等应用至关重要。然而，真实世界视频通常包含长序列，具有不规则的相机轨迹和未知的位姿，这会导致重建过程中的位姿漂移、特征错位和几何失真。此外，有损压缩通过引入不一致性放大了这些问题，这些不一致性会逐渐降低几何和渲染质量。尽管最近的研究已分别针对长序列新视角合成或无位姿重建进行了探索，但压缩感知方法仍侧重于特定伪影或有限场景，对长视频中多样化的压缩模式研究不足。本文提出CompSplat，一种压缩感知训练框架，该框架显式建模逐帧压缩特性，以减轻帧间不一致性和累积的几何误差。CompSplat结合了压缩感知的帧加权策略和自适应剪枝策略，以增强鲁棒性和几何一致性，特别是在重度压缩条件下。在包括Tanks and Temples、Free和Hike在内的多个具有挑战性的基准数据集上进行的大量实验表明，CompSplat实现了最先进的渲染质量和位姿精度，在严重压缩条件下显著超越了大多数最新的先进新视角合成方法。