Flame3D: エージェント型言語モデルによる3Dシーンのゼロショット合成的推論
Flame3D: Zero-shot Compositional Reasoning of 3D Scenes with Agentic Language Models
3Dシーン理解を、訓練なしで既製のMLLMと編集可能な視覚・テキスト3Dメモリ、合成可能な空間ツールを用いて実現するフレームワークを提案。推論時に空間操作を合成することで、複雑な幾何学的関係や未存在オブジェクトの推論を可能にした。
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: Sagar Bharadwaj, Ziyong Ma, Anurag Ghosh, Srinivasan Seshan, Anthony Rowe
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
3D scene understanding spans reasoning about free space, object grounding, hypothetical object insertions, complex geometric relationships, and integrating all of these with external tools and data sources. Existing 3D understanding methods typically rely on large-scale 3D-language training or focus on object grounding and simple spatial relationships. We argue that the broad generalization that motivates 3D-language training can be achieved at inference time, without 3D-specific training. We propose Flame3D, a training-free framework that represents scenes as editable visual-textual 3D memories and exposes them to an off-the-shelf MLLM through composable spatial tools. Flame3D also lets the agent synthesize custom spatial programs at inference time, enabling open-ended reasoning over layouts, empty space, and objects not yet present in the scene. External data and corrections can be added to the memory without retraining. In addition to showing competitive performance to finetuned 3D-LMM methods on ScanQA, we study multi-hop 3D reasoning capabilities of Flame3D by evaluating it on a curated compositional spatial-reasoning benchmark, Compose3D. We find that fixed tools fall short and that the agent's ability to synthesize spatial operations at inference time is essential. These results invite the question: should future progress in 3D scene understanding focus on richer scene memories and expressive compositional abstractions?
