Yehe Liu — accepted AI-conference papers

2025

Fix False Transparency by Noise Guided Splatting

Aly El Hakie, Yiren Lu, Yu Yin, Michael W. Jenkins, Yehe Liu

NeurIPS 2025poster

Opaque objects reconstructed by 3D Gaussian Splatting (3DGS) often exhibit a falsely transparent surface, leading to inconsistent background and internal patterns under camera motion in interactive viewing. This issue stems from the ill-posed optimization in 3DGS. During training, background and for…

Cited by 0 Source ↗Scholar ↗

2024

bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction

Yehe Liu, Alexander Krull, Hector Basevi, Ales Leonardis, Michael W. Jenkins

NeurIPS 2024poster

Quanta image sensors, such as SPAD arrays, are an emerging sensor technology, producing 1-bit arrays representing photon detection events over exposures as short as a few nanoseconds. In practice, raw data are post-processed using heavy spatiotemporal binning to create more useful and interpretable…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗