{"slug": "uniquery4r-unified-4d-scene-reconstruction-from-a-single-query", "title": "UniQuery4R: Unified 4D Scene Reconstruction from a Single Query", "summary": "Researchers introduced UniQuery4R, a query-conditioned framework for unified 4D scene reconstruction that encodes a multi-frame clip once and selects source and target views at decoding time, achieving the best macro-average results on WorldTrack for scene-flow estimation and dynamic-point reconstruction among evaluated methods.", "body_md": "arXiv:2608.17283v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/uniquery4r-unified-4d-scene-reconstruction-from-a-single-query", "canonical_source": "https://arxiv.org/abs/2608.17283", "published_at": "2026-08-19 04:00:00+00:00", "updated_at": "2026-08-19 04:13:01.279921+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning"], "entities": ["UniQuery4R", "WorldTrack"], "alternates": {"html": "https://wpnews.pro/news/uniquery4r-unified-4d-scene-reconstruction-from-a-single-query", "markdown": "https://wpnews.pro/news/uniquery4r-unified-4d-scene-reconstruction-from-a-single-query.md", "text": "https://wpnews.pro/news/uniquery4r-unified-4d-scene-reconstruction-from-a-single-query.txt", "jsonld": "https://wpnews.pro/news/uniquery4r-unified-4d-scene-reconstruction-from-a-single-query.jsonld"}}