Complet4R: Geometric Complete 4D Reconstruction

Weibang Wang; Kenan Li; Zhuoguang Chen; Yijun Yuan; Hang Zhao

cs.CVMar 28, 2026

Complet4R: Geometric Complete 4D Reconstruction

Authors: Weibang Wang, Kenan Li, Zhuoguang Chen, Yijun Yuan, Hang Zhao

Organizations: IIIS, Tsinghua University · Shanghai Artificial Intelligence Laboratory · Shanghai Qi Zhi Institute

Abstract

We introduce Complet4R, a novel end-to-end framework for Geometric Complete 4D Reconstruction, which aims to recover temporally coherent and geometrically complete reconstruction for dynamic scenes. Our method formalizes the task of Geometric Complete 4D Reconstruction as a unified framework of reconstruction and completion, by directly accumulating full contexts onto each frame. Unlike previous approaches that rely on pairwise reconstruction or local motion estimation, Complet4R utilizes a decoder-only transformer to operate all context globally directly from sequential video input, reconstructing a complete geometry for every single timestamp, including occluded regions visible in other frames. Our method demonstrates the state-of-the-art performance on our proposed benchmark for Geometric Complete 4D Reconstruction and the 3D Point Tracking task. Code will be released to support future research.

Figures & tables

Figure 2: Geometric 4D complete reconstruction from observations. Given input frames, Complet4R aggregates contextual information across all timestamps. Consequently, at each timestamp $T$ , the reconstructed scene incorporates the geometry from frame $T$ along with complementary information from all other frames.

Figure 3: Architecture Overview. By concatenating special aggregation tokens, Complet4R identifies the specific timestamp for aggregation. The Aggregation head then outputs the positions of 3D points from other views at this timestamp, aggregating 3D point maps across frames to form a complete geometric representation.

	Acc. $\downarrow$		Complet. $\downarrow$		N.C. $\uparrow$
Methods	Mean	Med.	Mean	Med.	Mean	Med.
St4RTrack-seq	0.92	0.71	3.10	0.17	0.48	0.47
St4RTrack-pairs	0.94	0.77	2.67	0.14	0.46	0.44
Complet4R (Ours)	0.50	0.37	0.26	0.11	0.49	0.49

Table 1: 4D Complete Reconstruction on SAIL-VOS 3D-test. We report Accuracy (Acc.), Completion (Complet.), and Normal Consistency (N.C.) on all points; each metric is shown as Mean and Median. Best results are bold .

		PO		DR		ADT		PStudio
Category	Methods	APD $\uparrow$	EPE $\downarrow$	APD $\uparrow$	EPE $\downarrow$	APD $\uparrow$	EPE $\downarrow$	APD $\uparrow$	EPE $\downarrow$
Combinational	SpaTracker+RANSAC-Procrustes	53.77	43.58	58.58	104.44	66.49	16.00	52.05	42.66
Combinational	SpaTracker+MonST3R	58.61	40.85	59.21	91.36	69.94	15.11	50.16	48.37
Feed-forward	MonST3R	39.36	64.52	51.86	53.13	67.92	15.78	51.32	45.68
	SpaTracker	51.20	46.95	58.65	108.28	67.65	16.28	62.59	30.94
	St4RTrack	68.72	29.70	68.13	29.61	75.34	12.12	69.67	26.37

Table 2: World Coordinate 3D Point Tracking on Dynamic Points. We report both APD and EPE for four datasets: PO (Point Odyssey), DR (Dynamic Replica), ADT (Aria Digital Twin), and PStudio (Panoptic Studio). Best results are bold .

Figure 4: Qualitative Results for 4D Complete Reconstruction. The first column shows the video inputs, with red boxes indicating the target aggregation timestamp for each sequence ( Agg. : aggregation). The subsequent columns present the outputs of different models. Our method successfully reconstructs the complete geometry at the target timestamp highlighted by the red ellipses, whereas other methods produce incomplete or geometrically inconsistent reconstructions.

Figure 5: Qualitative Results for 3D Dynamic Point Tracking. The first column shows the input images; the second and third columns display the tracking trajectories produced by our method at successive time steps. The smooth trajectories demonstrate strong spatiotemporal geometric consistency.

Variants	Loss	Agg. Repre.	Agg. Token	Mean	Med.	Mean	Med.	Mean	Med.
				Acc. $\downarrow$		Complet. $\downarrow$		N.C. $\uparrow$
(1)	Dynamic	-	-	0.50	0.47	0.26	0.20	0.48	0.47
(2)	-	Offset	-	0.63	0.42	0.50	0.11	0.44	0.40
(3)	-	-	Add	0.57	0.38	0.32	0.12	0.50	0.49
Complet4R (Ours)	Focal	Endpoint	Concatenate	0.50	0.37	0.26	0.11	0.49	0.49

Table 3: Ablation Study on 4D Complete Reconstruction on SAIL-VOS 3D-test. Accuracy (Acc.), Completion (Complet.), and Normal Consistency (N.C.) are reported over all points; each metric includes Mean and Median. Agg. Repre. means the aggregation representation, Agg. Token means aggregation tokens. Best results are bold . The symbol “-” indicates the default setting same as Complet4R.

		PO		DR		ADT		PStudio
Category	Methods	APD $\uparrow$	EPE $\downarrow$	APD $\uparrow$	EPE $\downarrow$	APD $\uparrow$	EPE $\downarrow$	APD $\uparrow$	EPE $\downarrow$
Combinational	SpaTracker+RANSAC-Procrustes	61.00	33,38	61.65	37.20	88.65	5.96	67.82	26.60
Combinational	SpaTracker+MonST3R	61.78	32.90	61.88	36.81	87.32	4.85	64.32	29.71
Feed-forward	MonST3R	48.95	47.68	55.36	38.72	84.73	7.20	64.11	30.15
	SpaTracker	60.49	33.74	61.32	37.50	87.68	6.16	80.76	16.50
	St4RTrack	67.43	28.70	67.90	26.27	85.34	6.88	76.97	19.69

Table 4: World Coordinate 3D Point Tracking on Dynamic Points with Global SIM(3) Alignment.

	Sintel		BONN		KITTI
Method	Abs Rel $\downarrow$	$\delta$ < $1.25\uparrow$	Abs Rel $\downarrow$	$\delta$ < $1.25\uparrow$	Abs Rel $\downarrow$	$\delta$ < $1.25\uparrow$
VGGT	0.298	68.1	0.057	96.8	0.061	97.0
CUT3R	0.421	47.9	0.078	93.7	0.118	88.1
Ours	0.353	63.9	0.066	95.9	0.079	94.9

Table 5: Evaluation on Video Depth Estimation.

	Sintel			ScanNet
Method	ATE $\downarrow$	RPE trans $\downarrow$	RPE rot $\downarrow$	ATE $\downarrow$	RPE trans $\downarrow$	RPE rot $\downarrow$
VGGT	0.168	0.065	0.477	0.035	0.015	0.380
CUT3R	0.213	0.066	0.621	0.099	0.022	0.600
Ours	0.215	0.089	1.081	0.050	0.023	0.549

Table 6: Evaluation on Camera Pose Estimation.

Frames	2	4	8	16	32	64	128	256
Time (s)	0.10	0.15	0.26	0.51	1.16	2.95	8.53	27.86
Mem. (GB)	7.0	7.6	9.0	10.2	12.6	15.1	18.0	28.6

Table 7: Runtime and GPU memory consumption for different sequence lengths. Runtime is measured in seconds, and GPU memory usage is reported in gigabytes.

Figure 6: More Qualitative Results for 4D Complete Reconstruction. The first column shows the video inputs, with red boxes indicating the target aggregation timestamp for each sequence ( Agg. : aggregation). The subsequent columns present the outputs of different models. Our method successfully reconstructs the complete geometry at the target timestamp highlighted by the red ellipses, whereas other methods produce incomplete or geometrically inconsistent reconstructions.

Figure 7: Comparison with DreamScene4D. The left shows the video inputs, while the right presents the reconstruction results: (a) from DreamScene4D, and (b) from our method. Our approach demonstrates higher reconstruction quality.

Figure 8: More Qualitative Results for 3D Dynamic Point Tracking. The first column shows the input images; the second and third columns display the tracking trajectories produced by our method at successive time steps. The smooth trajectories demonstrate strong spatiotemporal geometric consistency.

4D Reconstruction

4D reconstruction recovers changing 3D scenes, shapes, and motion over time from images, videos, or other sparse measurements.

See all 139 papers

DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds
Jun 10, 2026Weirong Chen, Keisuke Tateno, Hidenobu Matsuki +3Point Cloud Completion 4D Reconstruction
TU Munich · Google · Munich Center for Machine Learning
SM4RT: Learning Structured Motion Geometry for 4D Reconstruction
Jul 24, 2026Shing Ho J. Lin, Wenzhao Zheng, Dong Zhuo +33D ViTs 4D Reconstruction
Intelligent Vision Group, Tsinghua University
Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors
Apr 10, 2026Ying Zang, Yidong Han, Chaotao Ding +8UQ for 3D Reconstruction Dynamic Scene Reconstruction
Huzhou University · KOKONI 3D, Moxin Technology · Univeristy of Science and Technology of China +3

Jun 10, 2026J/K move · Enter open · S save

DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds

Weirong Chen, Keisuke Tateno, Hidenobu Matsuki, Michael Niemeyer+2

TU Munich · Google · Munich Center for Machine Learning

Point Cloud Completion 4D Reconstruction 3D Reconstruction Point Cloud Learning Dynamic Scene Reconstruction

Open paper AskPDF arXiv

We address 4D reconstruction from partial point cloud sequences, where depth-sensor observations are incomplete, unordered, and lack explicit temporal correspondences. This geometry-only setting is challenging due to missing observations and ambiguous dynamics. While recent progress has largely relied on image-based methods, existing point-based approaches typically focus on single objects, assume relatively complete inputs, or require explicit correspondences. To address these limitations, we propose DynaTok, a point-based framework for correspondence-free 4D reconstruction from partial point cloud sequences without images. DynaTok encodes frames into compact latent tokens, aggregates incomplete observations over time with a Transformer-based spatiotemporal encoder, and decouples geometry and motion through residual tokens in a unified model. A flow-matching decoder then reconstructs complete, temporally consistent 4D point-cloud sequences conditioned on the latent tokens. Experiments on object- and scene-level benchmarks demonstrate improved reconstruction quality and temporal coherence from partial point cloud observations. Project page: https://wrchen530.github.io/dynatok/.

Abstract

4D Reconstruction

Explore similar work

DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds

SM4RT: Learning Structured Motion Geometry for 4D Reconstruction

Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors