Search papers, labs, and topics across Lattice.
To overcome severe interpolation and field-of-view artifacts in conventional 4-analyzer polarimetric vision datasets, the authors built DensePol, a dataset of 2,018 paired RGB-polarization scenes captured via Division-of-Time acquisition across 180 full-resolution angles at $1^\circ$ intervals. High-density angular sampling provides the noise redundancy needed to train a deterministic diffusion framework equipped with cyclic AoLP representations and a local DoLP refiner. By replacing sparse microgrid measurements with dense temporal captures, polarimetric stability improves dramatically, reducing AoLP deviation from $13.36^\circ$ to $2.21^\circ$ and yielding superior downstream surface normal predictions.
Hardware interpolation artifacts in standard 4-analyzer polarization sensors quietly corrupt polarimetric ground truth, but dense 180-angle temporal sampling slashes AoLP error from $13.36^\circ$ to $2.21^\circ$ to unlock clean RGB-to-polarization synthesis.
Polarimetric vision is gaining increasing attention because it provides physical cues about scene shape, material, and reflection that are difficult to recover from RGB alone. Recent work has therefore explored predicting polarization directly from conventional RGB images; however, the fidelity of these methods strongly depends on the polarization supervision used for training. Most existing datasets rely on Division-of-Focal-Plane (DoFP) cameras with four spatially interleaved analyzer orientations, which provide limited angular redundancy and introduce interpolation and instantaneous-field-of-view errors. We introduce DensePol, a high-redundancy RGB--polarization dataset based on Division-of-Time (DoT) acquisition, capturing 180 full-resolution analyzer orientations at $1^\circ$ intervals. DensePol contains 2,018 paired RGB--polarization images with the angular measurements and fitting residuals retained. Dense angular sampling substantially improves polarization stability, reducing AoLP deviation from $13.36^\circ$ to $2.21^\circ$. We further introduce a deterministic diffusion-based RGB-to-polarization framework with cyclic AoLP representation and a local DoLP refiner. Experiments demonstrate improved polarization prediction and downstream surface-normal estimation. The dataset and code will be publicly available.
