用点对齐表示实现驾驶场景快速高保真重建
PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
- 以世界空间稀疏点查询为基础，融合多视角信息
- 在单次前向传播中实现跨视图一致性，消除重叠伪影
- 通过场景图建模动态物体，支持时序一致的运动传播
高保真驾驶场景重建对自动驾驶至关重要。尽管近期前向式3D高斯泼溅（3DGS）方法实现了快速重建，但其基于像素的高斯预测范式常导致多视角不一致和层叠伪影。现有方法通常通过密集光流预测建模动态物体，缺乏显式的跨视图对应关系和实例级一致性。本文提出PointForward，一种基于点对齐表示的前向驾驶场景重建框架。不同于像素对齐方法，我们在世界空间初始化稀疏3D查询，并通过时空融合将多视角图像信息聚合到这些查询上，在单次前向传播中强制实现显式的跨视图一致性。为处理场景动态性，我们引入场景图，显式组织重建过程中的移动实例。借助3D边界框，该方法可实现实例级运动传播和时序一致的动态表示。大量实验表明，PointForward在大规模驾驶基准上达到最先进性能。代码将在论文发表后公开。
原文摘要 · Abstract (English)
High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their per-pixel Gaussian prediction paradigm often suffers from multi-view inconsistency and layering artifacts. Moreover, existing methods often model dynamic instances via dense flow prediction, which lacks explicit cross-view correspondence and instance-level consistency. In this paper, we propose PointForward, a feedforward driving reconstruction framework through point-aligned representations. Unlike pixel-aligned methods, we initialize sparse 3D queries in world space and aggregate multi-view image information via spatial-temporal fusion onto these queries, enforcing explicit cross-view consistency in a single feedforward pass. To handle scene dynamics, we introduce scene graphs that explicitly organize moving instances during reconstruction. By leveraging 3D bounding boxes, our method enables instance-level motion propagation and temporally consistent dynamic representations. Extensive experiments demonstrate that PointForward achieves state-of-the-art performance on large-scale driving benchmarks. The code will be available upon the publication of the paper.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。