LiDPM: LiDARシーン補完のための点群拡散モデルの再考
LiDPM: Rethinking Point Diffusion for Lidar Scene Completion
LiDAR点群のシーン補完において、局所拡散の近似を不要にし、適切な開始点を持つ通常のDDPMで高精度な補完を実現した手法を提案。
著者: Tetiana Martyniuk, Gilles Puy, Alexandre Boulch, Renaud Marlet, Raoul de Charette
分類: cs.CV, cs.RO
原文アブストラクト
Training diffusion models that work directly on lidar points at the scale of outdoor scenes is challenging due to the difficulty of generating fine-grained details from white noise over a broad field of view. The latest works addressing scene completion with diffusion models tackle this problem by reformulating the original DDPM as a local diffusion process. It contrasts with the common practice of operating at the level of objects, where vanilla DDPMs are currently used. In this work, we close the gap between these two lines of work. We identify approximations in the local diffusion formulation, show that they are not required to operate at the scene level, and that a vanilla DDPM with a well-chosen starting point is enough for completion. Finally, we demonstrate that our method, LiDPM, leads to better results in scene completion on SemanticKITTI. The project page is https://astra-vision.github.io/LiDPM .
