潜在空間で進化する4D世界をモデリングする動的空間推論フレームワークPros4D
Pros4D: Modeling Evolving 4D Worlds in Latent Space for Dynamic Spatial Reasoning
単眼動画から観測済みの動的3D環境を潜在状態に圧縮し、それを自己回帰的に未来へ展開することで、観測範囲を超えた未来の動きも予測できる4D空間推論モデルを提案した。
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: Rongxin Gao, Dongxuan Liu, Chu Li, Chengyang Ji, Jialing Huang, Runyu Chen, Kairun Wen, Chenxin Li, Jingrui Ye, Haosong Zhen, Xinghao Ding, Yue Huang, Yuzhi Huang, Xiaodong Tu, Jingyan Jiang
分類: cs.CV
原文アブストラクト
Dynamic spatial reasoning from monocular video enables vision-language models (VLMs) to understand how 3D environments evolve over time, supporting physical world understanding and embodied intelligence. Existing efforts primarily address observed-dynamics understanding, whereas agents in dynamic environments also require future-dynamics prediction beyond the observation boundary. Moreover, external geometric processing and textual descriptions can increase inference complexity or lose information when representing continuous dynamics. These limitations motivate a shared internal state that preserves observed dynamics and remains predictive beyond the input video. Accordingly, we present Pros4D, a framework for modeling evolving 4D worlds in latent space that unifies retrospective understanding of observed-dynamics with prospective reasoning for future-dynamics prediction. Specifically, Pros4D-Engine derives geometry-grounded supervision and constructs paired examples for both tasks, while Pros4D-Bench evaluates them across eight spatial task categories spanning dynamic cameras, objects, and scenes. At the model level, Pros4D compresses observed dynamics into latent observed states and autoregressively rolls them forward into latent future states. 4D Latent Alignment (4DLA) grounds these states through complementary visual-semantic and geometric supervision, while joint language supervision connects them to task reasoning. Experiments across benchmarks show consistent improvements over strong baselines in both capabilities.
