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

arXiv: https://arxiv.org/abs/2602.09816 · HTML: https://mlsanity.com/paper/2602.09816/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 53 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Builds on (most cited first, 30 of 35)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior](https://mlsanity.com/paper/2212.07388/) (2022)
- [VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction](https://mlsanity.com/paper/2402.17427/) (2024)
- [COLMAP-Free 3D Gaussian Splatting](https://mlsanity.com/paper/2312.07504/) (2023)
- [F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories](https://mlsanity.com/paper/2303.15951/) (2023)
- [Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections](https://mlsanity.com/paper/2403.15704/) (2024)
- [Progressively Optimized Local Radiance Fields for Robust View Synthesis](https://mlsanity.com/paper/2303.13791/) (2023)
- [Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach](https://mlsanity.com/paper/2412.03017/) (2024)
- [NeRF-SR: High-Quality Neural Radiance Fields using Supersampling](https://mlsanity.com/paper/2112.01759/) (2021)
- [Multi-Frame Quality Enhancement for Compressed Video](https://mlsanity.com/paper/1803.04680/) (2018)
- [NAN: Noise-Aware NeRFs for Burst-Denoising](https://mlsanity.com/paper/2204.04668/) (2022)
- [Compression-aware Training of Deep Networks](https://mlsanity.com/paper/1711.02638/) (2017)
- [Fast Object Detection in Compressed Video](https://mlsanity.com/paper/1811.11057/) (2018)
- [NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer](https://mlsanity.com/paper/2303.06919/) (2023)
- [Video compression dataset and benchmark of learning-based video-quality metrics](https://mlsanity.com/paper/2211.12109/) (2022)
- [COMISR: Compression-Informed Video Super-Resolution](https://mlsanity.com/paper/2105.01237/) (2021)
- [LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos](https://mlsanity.com/paper/2508.14041/) (2025)
- [CPGA: Coding Priors-Guided Aggregation Network for Compressed Video Quality Enhancement](https://mlsanity.com/paper/2403.10362/) (2024)
- [Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal](https://mlsanity.com/paper/2502.09873/) (2025)
- [SfM-Free 3D Gaussian Splatting via Hierarchical Training](https://mlsanity.com/paper/2412.01553/) (2024)
- [From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm](https://mlsanity.com/paper/2306.06388/) (2023)

## Built on by (most cited first, 1 of 1)

- [JSGS: JPEG State-Guided Supervision for 3D Gaussian Splatting from Mixed-Quality Views](https://mlsanity.com/paper/2608.08659/) (2026)

## Abstract (arXiv)

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.