Feed-forward 3D Gaussian Splatting (3DGS) enables efficient one-pass scene reconstruction, providing 3D representations for novel view synthesis without per-scene optimization. However, existing methods typically predict pixel-aligned primitives per-view, producing an excessive number of primitives in dense-view settings and offering no explicit control over the number of predicted Gaussians. To address this, we propose EcoSplat, the first efficiency-controllable feed-forward 3DGS framework that adaptively predicts the 3D representation for any given target primitive count at inference time. EcoSplat adopts a two-stage optimization process. The first stage is Pixel-aligned Gaussian Training (PGT) where our model learns initial primitive prediction. The second stage is Importance-aware Gaussian Finetuning (IGF) stage where our model learns rank primitives and adaptively adjust their parameters based on the target primitive count. Extensive experiments across multiple dense-view settings show that EcoSplat is robust and outperforms state-of-the-art methods under strict primitive-count constraints, making it well-suited for flexible downstream rendering tasks.
@article{arxiv.2512.18692,
title = {EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images},
author = {Jongmin Park and Minh-Quan Viet Bui and Juan Luis Gonzalez Bello and Jaeho Moon and Jihyong Oh and Munchurl Kim},
journal= {arXiv preprint arXiv:2512.18692},
year = {2025}
}
Comments
The first two authors contributed equally to this work (equal contribution). The last two authors advised equally to this work. Please visit our project page at https://kaist-viclab.github.io/ecosplat-site/