重點導讀
車上的 LiDAR 感測器只能記錄當時掃到的周遭環境,換個角度看會是什麼樣子,原本無法直接取得。
- NVIDIA Research 的 LidarVerse 能模擬不同 LiDAR 感測器的掃描結果,從新的視角重建場景、依地圖生成場景,也能即時預測感測器接下來會看到什麼。
- 團隊提供了論文和程式碼,讓人可以進一步瞭解這套方法。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
NVIDIA AI@NVIDIAAI
·6 天前
See a recorded driving scene from a viewpoint the vehicle never captured.
NVIDIA Research’s LidarVerse is the first model to simulate scans for different LiDAR sensors, which use lasers to capture surroundings in 3D. It can recreate scenes from new viewpoints, generate scenes from maps, and predict what a sensor will see next, all in real time.
Read the paper and get the code ➡️ https://t.co/mvaGUVMLjP
推文來源 · X (Twitter)在 X 參與討論