Jean-Daniel Nahmias — accepted AI-conference papers

2026

Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting

Yixing Lao, Xuyang BAI, Xiaoyang Wu, Nuoyuan Yan, Zixin Luo, Tian Fang +4

ICLR 2026poster

Existing feed-forward 3D Gaussian Splatting methods typically rely on pixel-aligned primitives, which makes scaling to higher resolutions (e.g., 4K) prohibitive as the number of Gaussians grows quadratically with image resolution. We introduce LGTM (Less Gaussians, Texture More), a feed-forward and…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Matrix3D: Large Photogrammetry Model All-in-One

Yuanxun Lu, Jingyang Zhang, Tian Fang, Jean-Daniel Nahmias, Yanghai Tsin, Long Quan +3

CVPR 2025highlight

We present Matrix3D, a unified model that performs several photogrammetry subtasks, including pose estimation, depth prediction, and novel view synthesis using just the same model. Matrix3D utilizes a multi-modal diffusion transformer (DiT) to integrate transformations across several modalities, suc…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗