# C3-GS: Learning Context-aware, Cross-dimension, Cross-scale Feature for Generalizable Gaussian Splatting

arXiv: https://arxiv.org/abs/2508.20754 · HTML: https://mlsanity.com/paper/2508.20754/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Builds on (most cited first, 29 of 29)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [Splatter Image: Ultra-Fast Single-View 3D Reconstruction](https://mlsanity.com/paper/2312.13150/) (2023)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis](https://mlsanity.com/paper/2312.02155/) (2023)
- [TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers](https://mlsanity.com/paper/2111.14600/) (2021)
- [Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement](https://mlsanity.com/paper/2003.13017/) (2020)
- [MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2405.12218/) (2024)
- [Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation](https://mlsanity.com/paper/2201.01501/) (2022)
- [Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking](https://mlsanity.com/paper/2007.10872/) (2020)
- [Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting](https://mlsanity.com/paper/2507.02939/) (2025)
- [MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth](https://mlsanity.com/paper/2208.02541/) (2022)
- [Explicit Correspondence Matching for Generalizable Neural Radiance Fields](https://mlsanity.com/paper/2304.12294/) (2023)
- [MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views](https://mlsanity.com/paper/2409.14316/) (2024)
- [DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2409.18092/) (2024)
- [SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Net](https://mlsanity.com/paper/2403.08885/) (2024)
- [SRKD: Towards Efficient 3D Point Cloud Segmentation via Structure- and Relation-aware Knowledge Distillation](https://mlsanity.com/paper/2506.17290/) (2025)
- [Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields](https://mlsanity.com/paper/2404.17528/) (2024)
- [EVLoc: Event-based Visual Localization in LiDAR Maps via Event-Depth Registration](https://mlsanity.com/paper/2503.00167/) (2025)
- [ICG-MVSNet: Learning Intra-view and Cross-view Relationships for Guidance in Multi-View Stereo](https://mlsanity.com/paper/2503.21525/) (2025)

## Abstract (arXiv)

Generalizable Gaussian Splatting aims to synthesize novel views for unseen scenes without per-scene optimization. In particular, recent advancements utilize feed-forward networks to predict per-pixel Gaussian parameters, enabling high-quality synthesis from sparse input views. However, existing approaches fall short in encoding discriminative, multi-view consistent features for Gaussian predictions, which struggle to construct accurate geometry with sparse views. To address this, we propose C3-GS, a framework that enhances feature learning by incorporating context-aware, cross-dimension, and cross-scale constraints. Our architecture integrates three lightweight modules into a unified rendering pipeline, improving feature fusion and enabling photorealistic synthesis without requiring additional supervision. Extensive experiments on benchmark datasets validate that C3-GS achieves state-of-the-art rendering quality and generalization ability. Code is available at: https://github.com/YuhsiHu/C3-GS.