UniQuery4R: Unified 4D Scene Reconstruction from a Single Query

2026-08-17

AI Summary

UniQuery4R通过一次编码多帧剪辑并在解码时选择视图，解决了动态4D场景重建中的计算冗余和特征重用问题。

Abstract

Reconstructing dynamic 4D scenes requires jointly estimating correspondence, geometry, object motion, and camera motion. Existing feed-forward methods typically predict dense task-specific maps or independently process source-target pairs, leading to unnecessary computation for sparse queries and limited feature reuse across different frame pairs. We present UniQuery4R, a query-conditioned framework that encodes a multi-frame clip once and selects the source view, target view, and continuous source-image coordinate only at decoding time via source-to-target cross-attention. Each query jointly predicts target correspondence, target-time 3D position, and scene flow, along with source depth, while camera parameters are estimated per view. This design allows the encoded clip to be reused across arbitrary source-target selections and supports both sparse inference and dense reconstruction through batched queries, without learned temporal embeddings tied to a fixed clip length. We further introduce a direction-magnitude parameterization of scene flow with separate supervision for moving and static points. Among the evaluated methods, UniQuery4R achieves the best macro-average results on WorldTrack for both scene-flow estimation and dynamic-point reconstruction.

Problem

• 4D Scene Reconstruction
• Sparse Queries
• Feature Reuse

Innovation

• query-conditioned framework
• source-to-target cross-attention
• direction-magnitude parameterization of scene flow