CompSplat: Compression-aware 3D Gaussian Splatting for Real-world Video

TL;DR

CompSplat is a novel framework that improves 3D Gaussian Splatting for real-world video view synthesis by explicitly modeling compression effects, leading to enhanced robustness and quality under heavy compression.

Contribution

It introduces a compression-aware training method with frame weighting and adaptive pruning to address artifacts caused by video compression in novel view synthesis.

Findings

Achieves state-of-the-art rendering quality under severe compression.

Significantly improves pose accuracy in challenging benchmarks.

Robustly handles diverse compression patterns in long videos.

Abstract

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.