FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenes

TL;DR

FreeSplat introduces a novel framework for generalizable 3D Gaussian Splatting that reconstructs geometrically consistent indoor scenes from long sequences, enabling high-quality free-view synthesis across wide view ranges.

Contribution

The paper proposes a new FreeSplat framework with adaptive cost volumes, pixel-wise triplet fusion, and a robust training strategy for improved free-view synthesis and scene reconstruction.

Findings

Achieves state-of-the-art view synthesis quality.

Reduces redundant Gaussians for efficient inference.

Performs well across varying numbers of input views.

Abstract

Empowering 3D Gaussian Splatting with generalization ability is appealing. However, existing generalizable 3D Gaussian Splatting methods are largely confined to narrow-range interpolation between stereo images due to their heavy backbones, thus lacking the ability to accurately localize 3D Gaussian and support free-view synthesis across wide view range. In this paper, we present a novel framework FreeSplat that is capable of reconstructing geometrically consistent 3D scenes from long sequence input towards free-view synthesis.Specifically, we firstly introduce Low-cost Cross-View Aggregation achieved by constructing adaptive cost volumes among nearby views and aggregating features using a multi-scale structure. Subsequently, we present the Pixel-wise Triplet Fusion to eliminate redundancy of 3D Gaussians in overlapping view regions and to aggregate features observed across multiple views. Additionally, we propose a simple but effective free-view training strategy that ensures robust view synthesis across broader view range regardless of the number of views. Our empirical results demonstrate state-of-the-art novel view synthesis peformances in both novel view rendered color maps quality and depth maps accuracy across different numbers of input views. We also show that FreeSplat performs inference more efficiently and can effectively reduce redundant Gaussians, offering the possibility of feed-forward large scene reconstruction without depth priors.