[
    {
        "id": "osp-17805",
        "type": "article-journal",
        "title": "DeltaSplat: Iterative Gaussian Refinement for Pose-Free Feed-Forward 3D Gaussian Splatting",
        "author": [
            {
                "family": "Park",
                "given": "Chanung"
            },
            {
                "family": "Song",
                "given": "Seunghyeon"
            },
            {
                "family": "Lee",
                "given": "Joo Chan"
            },
            {
                "family": "Park",
                "given": "Eunbyung"
            },
            {
                "family": "Ko",
                "given": "Jong Hwan"
            }
        ],
        "URL": "https://omanscience.com/en/articles/deltasplat-iterative-gaussian-refinement-for-pose-free-feed-forward-3d-gaussian-splatting",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Pose-free feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene from sparse, unposed images in a single network pass, removing the need for camera calibration and per-scene optimization. However, camera estimation errors propagate into the predicted Gaussians and compound the geometric and photometric inaccuracies of single-pass prediction. To correct these errors, we introduce DeltaSplat, a lightweight Gaussian refinement module for pose-free feed-forward 3DGS. It iteratively renders the current Gaussians at the input context views and predicts per-Gaussian updates from the resulting residuals. A 2D residual alone, however, underdetermines the 3D correction. DeltaSplat therefore conditions each update on per-pixel Plücker rays and rendered depth as a soft geometric prior. A dual-branch convolutional mixer efficiently encodes these inputs, and per-attribute heads decode the fused features into position, opacity, and color updates. The module adds only ~2.2% parameters to the backbone and remains fully feed-forward at inference. On DL3DV, DeltaSplat reaches 26.64 dB PSNR in the pose-free setting, improving its state-of-the-art backbone by 1.75 dB and surpassing even baselines supplied with ground-truth cameras; consistent gains hold across 6-24 views and all camera regimes."
    }
]