CVFeb 24

UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling

arXiv:2602.20943v12 citationsh-index: 4
Originality Incremental advance
AI Analysis

This work addresses the challenge of modeling long-range driving sequences for autonomous driving applications, representing an incremental improvement by hybridizing existing approaches.

The paper tackles the problem of efficient long-range 4D reconstruction for dynamic driving scenes, which is critical for autonomous driving simulation, by proposing UFO, a recurrent paradigm that combines optimization-based and feed-forward methods. The result shows that UFO significantly outperforms existing methods on the Waymo Open Dataset, reconstructing 16-second driving logs within 0.5 second while maintaining superior visual quality and geometric accuracy.

Dynamic driving scene reconstruction is critical for autonomous driving simulation and closed-loop learning. While recent feed-forward methods have shown promise for 3D reconstruction, they struggle with long-range driving sequences due to quadratic complexity in sequence length and challenges in modeling dynamic objects over extended durations. We propose UFO, a novel recurrent paradigm that combines the benefits of optimization-based and feed-forward methods for efficient long-range 4D reconstruction. Our approach maintains a 4D scene representation that is iteratively refined as new observations arrive, using a visibility-based filtering mechanism to select informative scene tokens and enable efficient processing of long sequences. For dynamic objects, we introduce an object pose-guided modeling approach that supports accurate long-range motion capture. Experiments on the Waymo Open Dataset demonstrate that our method significantly outperforms both per-scene optimization and existing feed-forward methods across various sequence lengths. Notably, our approach can reconstruct 16-second driving logs within 0.5 second while maintaining superior visual quality and geometric accuracy.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes