cs.CVNov 19, 2026

DfD-GS: Defocus Image Prior for Metric-Scale Single-View Depth Estimation and View Synthesis

Authors: Shiori Ueda, Rinto Yagawa, Hideo Saito, Shohei Mori

Organizations: Keio University · University of Stuttgart

Abstract

Recovering metric-scale geometry from observations at a single viewpoint remains fundamentally ill-posed, limiting the reliability of novel view synthesis. Recent methods rely on learned monocular depth priors, which provide strong structural estimates but can suffer from scale ambiguity and dataset-dependent biases. We propose DfD-GS, a feed-forward framework that predicts a metric-scale 3D Gaussian scene representation from a single-view all-in-focus--defocused image pair. The key idea is to exploit defocus blur as a physical metric depth cue. DfD-GS first estimates a defocus-based metric disparity map from the all-in-focus--defocused image pair and the corresponding defocus strength. This estimate is used to align and refine a monocular depth prior to metric scale. Visible and hidden 3D Gaussians are then predicted for occlusion-aware novel view synthesis. Experiments on synthetic-defocus datasets constructed from Booster and Middlebury show that DfD-GS outperforms single-image baselines in metric depth estimation and novel view synthesis. On WildRGB-D, DfD-GS achieves lower AbsRel and LPIPS but higher depth RMSE than the single-image baselines. Additional analyses show that DfD-GS maintains a more stable metric scale under field-of-view changes. Qualitative results on a real dataset show recovery of the main scene structure under optical defocus.

Figures & tables

Explore similar work

CardsList
  1. A Single Image and Multimodality Is All You Need for Novel View Synthesis

    Feb 20, 2026Amirhosein Javadi, Chi-Shiang Gau, Konstantinos D. Polyzos +1Novel View SynthesisDepth Estimation

  2. PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinement

    Apr 24, 2026David Recasens, Robert Maier, Aljaz Bozic +4Multi-View Depth EstimationDepth Estimation

  3. Zero-Shot Depth from Defocus

    Mar 27, 2026Yiming Zuo, Hongyu Wen, Venkat Subramanian +5Metric Depth EstimationDepth Estimation