LiDARCrafter: LiDAR系列からの動的4D世界モデリング
LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences
自然言語指示からLiDARの4Dシーケンスを生成・編集する統合フレームワークを提案し、nuScenesで最先端の忠実性・制御性・時間的一貫性を達成した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Ao Liang, Youquan Liu, Yu Yang, Dongyue Lu, Linfeng Li, Lingdong Kong, Huaici Zhao, Wei Tsang Ooi
分類: cs.CV, cs.RO
原文アブストラクト
Generative world models have become essential data engines for autonomous driving, yet most existing efforts focus on videos or occupancy grids, overlooking the unique LiDAR properties. Extending LiDAR generation to dynamic 4D world modeling presents challenges in controllability, temporal coherence, and evaluation standardization. To this end, we present LiDARCrafter, a unified framework for 4D LiDAR generation and editing. Given free-form natural language inputs, we parse instructions into ego-centric scene graphs, which condition a tri-branch diffusion network to generate object structures, motion trajectories, and geometry. These structured conditions enable diverse and fine-grained scene editing. Additionally, an autoregressive module generates temporally coherent 4D LiDAR sequences with smooth transitions. To support standardized evaluation, we establish a comprehensive benchmark with diverse metrics spanning scene-, object-, and sequence-level aspects. Experiments on the nuScenes dataset using this benchmark demonstrate that LiDARCrafter achieves state-of-the-art performance in fidelity, controllability, and temporal consistency across all levels, paving the way for data augmentation and simulation. The code and benchmark are released to the community.
