← Search

Tengkai Wang

1 accepted papers

2026

NoiseSDF2NoiseSDF: Learning Clean Neural Fields from Noisy Supervision

ICML 2026poster

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…

Cited by 0SourceScholar