NoiseSDF2NoiseSDF: Learning Clean Neural Fields from Noisy Supervision 事件

NoiseSDF2NoiseSDF: Learning Clean Neural Fields from Noisy Supervision arXiv:2507.13595v3 Announce Type: replace Abstract: Reconstructing accurate implicit surface representations from point clouds remains a challenging task, particularly when data is captured using low-quality scanning devices. These point clouds often contain substantial noise, leading to inaccurate surface reconstructions. Inspired by the Noise2Noise paradigm for 2D images, we introduce NoiseSDF2NoiseSDF, a novel method desi