π^4:用於 4D 場景幾何與運動的基礎模型
π^4: A Foundation Model for 4D Scene Geometry and Motion
π^4 是面向 4D 場景感知的統一基礎模型,可從未經標定的 RGB 圖像或影片中恢復稠密幾何、相機位姿和度量尺度,並為多圖輸入提供點追蹤及移動物體遮罩。在多項基準測試的幾何評估中,π^4 的整體平均排名最佳,2D/3D 點追蹤及移動物體分割表現具競爭力。完整系統約有 0.5B 參數,可在一次前向傳播中聯合重建與追蹤,處理數千張輸入圖像;訓練上下文最多為 64 個視角,程式碼和模型已提供。
Published on Nov 17
Authors:
,
,
,
,
,
Abstract
This unified foundation model enables the recovery of dense geometry, camera poses, and object tracking from diverse, uncalibrated observations in 4D scenes using a shared geometry and motion branch architecture.
π^4 is a unified foundation model for 4D scene perception. From diverse, uncalibrated RGB observations in the wild---a single image, an unordered collection, or a video sequence---it recovers dense geometry, camera poses, and metric scale, together with 2D/3D point tracks and moving-object masks for multi-image inputs. It couples a geometry branch with a geometry-conditioned motion branch, which predicts image-space correspondences that are lifted into 3D using reconstructed target-view geometry. Across diverse benchmarks, π^4 achieves the best overall average rank in geometry evaluation, alongside competitive performance in single- and multiview 2D/3D point tracking and moving-object segmentation. With a shared backbone, the full geometry-and-motion system contains approximately 0.5B parameters---less than half the size of most baselines. It produces joint reconstructions and tracks in one forward pass, including large-scale scenes with thousands of input images despite training with contexts of at most 64 views. We further present the data and training recipe underlying these capabilities, together with empirical studies of key design choices. Code and models are available at https://github.com/yyfz/Pi4.
View arXiv page View PDF Project page GitHub Add to collection
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.23144 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.23144 in a dataset README.md to link it from this page.
Spaces citing this paper 1
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co