AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors

Xiaozhen Qiao; Wenjia Wang; Zhiyuan Zhao; Jiacheng Sun; Ping Luo; Hongyuan Zhang; Xuelong Li

cs.CVFeb 27, 2026

AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors

Authors: Xiaozhen Qiao, Wenjia Wang, Zhiyuan Zhao, Jiacheng Sun, Ping Luo, Hongyuan Zhang, Xuelong Li

Organizations: Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China. · University of Science and Technology of China. · University of Hong Kong. · Huawei Technologies Co., Ltd..

Abstract

Reconstructing 3D humans from images captured at multiple perspectives typically requires pre-calibration, like using checkerboards or MVS algorithms, which limits scalability and applicability in diverse real-world scenarios. In this work, we present AHAP (Reconstructing Arbitrary Humans from Arbitrary Perspectives), a feed-forward framework for reconstructing arbitrary humans from arbitrary camera perspectives without requiring camera calibration. Our core lies in the effective fusion of multi-view geometry to assist human association, reconstruction and localization. Specifically, we use a Cross-View Identity Association module through learnable person queries and soft assignment, supervised by contrastive learning to resolve cross-view human identity association. A Human Head fuses cross-view features and scene context for SMPL prediction, guided by cross-view reprojection losses to enforce body pose consistency. Additionally, multi-view geometry eliminates the depth ambiguity inherent in monocular methods, providing more precise 3D human localization through multi-view triangulation. Experiments on EgoHumans and EgoExo4D demonstrate that AHAP achieves competitive performance on both world-space human reconstruction and camera pose estimation, while being 180 $\times$ faster than optimization-based approaches.

Figures & tables

Figure 1: (a) AHAP achieves 180 $\times$ speedup over optimization-based HSfM ( Müller et al., 2025 ) while maintaining competitive accuracy. (b) Results on EgoHumans. (c) Results on EgoExo4D.

Method	Feed-fwd	Multi-Person	Camera	Scene
Multi-HMR ( Baradel et al., 2024 )	✓	✓	✗	✗
SLAHMR ( Ye et al., 2023a )	✗	✓	✓	✗
UnCaliPose ( Xu and Kitani, 2022 )	✗	✓	✓	✗
HSfM ( Müller et al., 2025 )	✗	✓	✓	✓
HAMSt3R ( Rojas et al., 2025 )	✗	✓	✓	✓
AHAP (Ours)	✓	✓	✓	✓

Table 1: Comparison of method capabilities. AHAP is the first feed-forward method to jointly reconstruct scene geometry and cameras from uncalibrated arbitrary-view images.

Figure 2: Overall pipeline of AHAP. Given multi-view images, the scene encoder ( Lin et al., 2025 ) estimates scene geometry and camera poses, while the human encoder ( Baradel et al., 2024 ) extracts human-centric features. Our cross-view identity association module matches the same person across views via learnable queries. The human head fuses scene tokens, aggregated tokens, and reference view tokens through a multi-view fusion decoder to predict SMPL parameters. Finally, we align humans and scene point clouds via scale alignment and multi-view triangulation for precise human localization.

Figure 3: PCA visualization of feature distributions. (a-d) Scene encoder ( Lin et al., 2025 ) features; (e-h) Human encoder ( Baradel et al., 2024 ) features. Human encoder features show stronger semantic clustering aligned with ground truth, while scene encoder provides complementary geometric information.

Figure 4: Multi-view triangulation for human position refinement. For persons visible in multiple views, we refine their 3D positions using DLT triangulation based on 2D pelvis observations and estimated camera poses, improving human-scene alignment.

Type	Method	EgoHumans			EgoExo4D
Type	Method	W-MPJPE $\downarrow$	GA-MPJPE $\downarrow$	PA-MPJPE $\downarrow$	W-MPJPE $\downarrow$	PA-MPJPE $\downarrow$
Single-view	Multi-HMR ( Baradel et al., 2024 )	7.66	0.99	0.12	2.88	0.07
Optimization-based	UnCaliPose ( Xu and Kitani, 2022 )	3.51	0.67	0.13	2.90	0.13
	HSfM (init) ( Müller et al., 2025 )	4.28	0.51	0.06	5.29	0.07
	HSfM ( Müller et al., 2025 )	1.04	0.21	0.05	0.56	0.06
	HAMSt3R ( Rojas et al., 2025 )	3.80	0.42	0.14	0.51	0.09

Table 2: Human-centric evaluation metrics on EgoHumans and EgoExo4D. AHAP achieves competitive W-MPJPE (0.88m) and GA-MPJPE (0.18m) on EgoHumans, outperforming optimization-based HSfM by 15%. While HSfM attains lower PA-MPJPE through iterative refinement, our feed-forward approach remains competitive (0.08m vs. 0.05m) without test-time optimization. Best and second best results are highlighted.

Type	Method	EgoHumans						EgoExo4D
Type	Method	TE $\downarrow$	s-TE $\downarrow$	AE $\downarrow$	RRA@10 $\uparrow$	CCA@10 $\uparrow$	s-CCA@10 $\uparrow$	TE $\downarrow$	s-TE $\downarrow$	AE $\downarrow$	RRA@10 $\uparrow$	CCA@10 $\uparrow$	s-CCA@10 $\uparrow$
Opt.-based	UnCaliPose ( Xu and Kitani, 2022 )	2.63	2.63	60.90	0.28	-	0.33	2.43	1.16	65.61	0.19	-	0.24
	HSfM (init) ( Müller et al., 2025 )	2.37	1.15	11.00	0.52	0.26	0.49	1.27	0.33	9.92	0.81	0.05	0.64
	HSfM ( Müller et al., 2025 )	2.09	0.75	9.35	0.72	0.32	0.75	0.95	0.36	11.57	0.78	0.07	0.67
	HAMSt3R ( Rojas et al., 2025 )	2.33	0.40	10.24	0.77	0.06	0.75	0.60	0.15	2.85	0.99	0.42	0.87
FF	DA3 ( Lin et al., 2025 )	3.89	0.27	2.26	0.99	-	0.86	1.62	0.07	1.80	0.98	0.02	0.96

Table 3: Camera pose evaluation on EgoHumans and EgoExo4D. Feed-forward methods achieve superior rotation accuracy: AHAP obtains AE of 1.47° on EgoHumans (vs. HSfM’s 9.35°) with perfect RRA@10 of 1.00. Compared to DA3, AHAP improves rotation accuracy by 35% (AE: 1.47° vs. 2.26°) and scale-aligned translation by 41% (s-TE: 0.16m vs. 0.27m), demonstrating that joint human-scene learning provides mutually beneficial geometric priors. Best and second best results are highlighted.

Method	Num. Views
Method	1	2	3	4
HSfM ( Müller et al., 2025 )	-	180.41s	201.85s	208.67s
AHAP (Ours)	0.34s	0.72s (250 $\times$ )	0.94s (215 $\times$ )	1.16s (180 $\times$ )

Table 4: Efficiency comparison. Our method achieves 180–250

\times

speedup over HSfM across different numbers of views.

Panel of Figure 5 — Figure 5: Qualitative results. Visualization of human-scene reconstruction on EgoHumans and EgoExo4D. AHAP produces accurate human meshes within reconstructed scenes, maintaining consistent identity association across views.

Figure 7: Ablation study on backbone variants. We evaluate combinations of DA3 (Large/Giant) and Multi-HMR (672B/672L/896L) backbones. Giant variants excel in camera metrics while 896L improves human reconstruction.

Method	W-MPJPE $\downarrow$	GA-MPJPE $\downarrow$	PA-MPJPE $\downarrow$
w/o $\mathcal{L}_{\text{reproj}}$	1.33	0.25	0.12
w/o $\mathcal{L}_{\text{assign}}$	1.33	0.24	0.11
w/o $\mathcal{L}_{\text{contra}}$	1.30	0.23	0.12
w/o $\mathcal{L}_{\text{assign + contra}}$	1.47	0.39	0.14
w/o triangulation	0.91	0.19	0.08
Full Model	0.88	0.18	0.08

Table 5: Ablation study on key components on EgoHumans.

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Activity	Sequences	Cameras
01_tagging	001–014	1, 4, 6, 8
02_lego	001–006	2, 3, 4, 6
03_fencing	001–014	4, 5, 10, 13
04_basketball	001–014	1, 3, 4, 8
05_volleyball	001–011	2, 4, 8, 11
06_badminton	001–061	1, 2, 5, 7

Appendix

Table 6: EgoHumans evaluation sequences and camera configurations.

Dataset	Takes / Frame Indices	Dataset	Takes / Frame Indices
cmu_soccer	06_3/1426, 12_2/6807, 16_2/6373	unc_basketball	02-24-23_01_3/84, 02-24-23_02_10/466, 02-24-23_02_11/927, 03-30-23_02_10/45, 03-30-23_02_14/7, 03-30-23_02_15/40, 03-30-23_02_17/9, 03-30-23_02_18/20, 03-30-23_02_19/7, 03-30-23_02_4/107, 03-30-23_02_5/25, 03-30-23_02_7/1141
georgiatech_bike	06_12/170, 06_2/97, 06_6/74, 06_8/15, 07_10/28, 07_12/38, 07_2/97, 07_4/46, 07_6/67, 07_8/138, 14_12/593, 14_2/1214, 14_6/575, 14_8/97, 15_2/1508, 15_4/844, 15_6/1103, 15_8/3153, 16_2/882, 16_6/3031, 16_8/1274	uniandes_basketball	001_23/768, 001_24/1386, 001_26/146, 001_27/439, 003_38/32, 004_23/369, 004_44/261, 004_45/667
georgiatech_covid	02_10/2227, 02_12/6974, 02_14/2926, 02_2/67, 02_4/67, 04_10/999, 04_12/6160, 04_4/2996, 04_6/4528, 06_2/47, 06_4/64, 18_10/5524, 18_12/3457, 18_2/2413, 18_4/3534, 18_6/4389, 18_8/458	uniandes_dance	002_11/201, 002_2/439, 008_29/276, 008_30/166, 008_31/31, 008_32/11, 008_33/1105, 008_34/753, 008_35/607, 008_36/1045, 008_37/913, 008_38/706, 016_10/841, 016_11/279, 016_12/932, 016_13/453, 016_14/951, 016_30/577, 016_31/1709, 016_32/377, 016_33/1158, 016_36/1247, 016_37/145, 016_38/1416, 016_39/399, 016_3/1239, 016_42/1406, 016_43/1271, 016_44/1268, 016_45/838, 016_6/1361, 016_7/1040, 016_8/1488, 017_6/1592, 019_17/1003, 019_18/509, 019_19/1537, 019_20/1089, 019_22/81, 019_24/484, 019_25/183, 019_26/1814, 019_27/283, 019_28/1411, 019_46/412, 019_47/790, 019_49/1617, 019_51/481, 019_52/875, 019_54/766, 019_55/679, 019_56/561, 019_57/1073, 019_58/192, 024_11/1619, 024_12/104, 024_13/1419, 024_14/1180, 024_15/378, 024_16/1569, 024_17/1317, 024_45/844, 024_47/732, 024_48/261, 024_49/325
iiith_cooking	59_2/7795, 64_2/298, 89_6/1177, 90_4/1383	upenn_Dance	0706_4_2/2512, 0706_4_3/1277, 0706_4_4/1670, 0706_4_5/1904, 0713_3_2/164, 0713_3_3/586, 0713_3_4/0, 0713_3_5/243, 0713_4_2/125, 0713_4_3/1280, 0713_4_4/308, 0713_4_5/262, 0713_5_4/238, 0713_5_6/2534
iiith_soccer	015_2/1610	upenn_Piano	0721_1_2/140, 0721_1_3/648, 0722_1_2/83, 0727_Partner_Dance_3_1_2/62
nus_cpr	12_1/1338, 12_2/76	utokyo_pcr	2001_29_2/5799, 2001_29_4/3491, 2001_29_6/550, 2001_30_2/2121, 2001_30_4/1696, 2001_32_2/6641, 2001_32_4/6048

Appendix

Table 7: EgoExo4D evaluation takes and frame indices.

DA3	Multi-HMR	Human Metrics			Camera Metrics
DA3	Multi-HMR	W-MPJPE $\downarrow$	GA-MPJPE $\downarrow$	PA-MPJPE $\downarrow$	TE $\downarrow$	s-TE $\downarrow$	AE $\downarrow$	RRA@10 $\uparrow$	s-CCA@10 $\uparrow$
Large	672_B	0.94	0.19	0.09	4.46	0.24	2.69	1.00	0.94
Large	672_L	0.92	0.18	0.08	4.45	0.23	2.69	0.99	0.95
Large	896_L	0.83	0.19	0.09	4.55	0.22	2.68	0.99	0.96
Giant	672_B	1.11	0.19	0.09	4.34	0.19	1.50	1.00	0.96
Giant	672_L	1.10	0.20	0.10	4.36	0.19	1.50	1.00	0.97

Appendix

Table 8: Ablation study on backbone variants on EgoHumans. Best and second best results are highlighted.

Num. Views	Human Metrics			Camera Metrics
Num. Views	W-MPJPE $\downarrow$	GA-MPJPE $\downarrow$	PA-MPJPE $\downarrow$	TE $\downarrow$	s-TE $\downarrow$	AE $\downarrow$	RRA@10 $\uparrow$	s-CCA@10 $\uparrow$
1	1.54	0.16	0.16	-	-	-	-	-
2	0.93	0.25	0.09	4.72	0.17	2.02	1.00	1.00
3	0.90	0.23	0.08	4.79	0.17	1.63	1.00	0.87
4	0.88	0.18	0.08	4.54	0.16	1.47	1.00	0.98

Appendix

Table 9: Ablation study on the number of views on EgoHumans. Best and second best results are highlighted.

Figure 8: Additional qualitative results. Our method accurately reconstructs the 3D poses of two individuals (shown in orange and green) and recovers the camera poses from five different viewpoints. The scene point cloud and camera frustums are visualized together with the SMPL meshes, demonstrating consistent multi-view reconstruction.

Figure 9: Additional qualitative results. Our method successfully handles complex real-world scenarios with cluttered backgrounds, diverse objects, and varying camera viewpoints. The reconstructed human (shown in blue) is accurately localized across 5 different camera views, demonstrating robustness to challenging scene conditions.

Figure 10: Failure case. The reconstructed human meshes appear floating above the ground plane, with feet not properly aligned with the floor surface.

Explore similar work

Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation
Sep 1, 2026Yuanwang Yang, Buzhen Huang, Zongxuan Ren +2Multi-View 3D Reconstruction 3D Human Reconstruction
College of Intelligence and Computing, Tianjin University, 135 Yaguan Road, Tianjin, 300350, Tianjin, China.
HARMONI: Aligning Human and Scene Priors for Multi-View 4D Reconstruction
Mar 13, 2026Sangmin Kim, Minhyuk Hwang, Geonho Cha +23D Reconstruction Multi-View 3D Reconstruction
Seoul National University · NAVER Cloud
Unconstrained Multi-view Human Pose Estimation with Algebraic Priors
Apr 27, 2026Xiaolin Qin, Qianlei Wang, Jiacen Liu +3Multi-View Geometry 3D Human Pose Estimation
Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu 610213, China · School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 101408, China · School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China. +2

Sep 1, 2026J/K move · Enter open · S save

Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation

Yuanwang Yang, Buzhen Huang, Zongxuan Ren, Jing Huang+1

College of Intelligence and Computing, Tianjin University, 135 Yaguan Road, Tianjin, 300350, Tianjin, China.

Multi-View 3D Reconstruction 3D Human Reconstruction 3D Representation Learning Feed-Forward 3D Reconstruction

Open paper AskPDF arXiv

Multi-view human reconstruction has been extensively studied under simplified settings, yet robust and efficient multi-person reconstruction in unconstrained environments remains challenging. Existing bottom-up methods often rely on accurate camera calibration and explicit cross-view matching, and therefore struggle with severe occlusions and ambiguities. We propose a new top-down paradigm that maintains a unified, instance-centric human-aware 3D space, enabling simultaneous camera calibration, cross-view association, and human reconstruction via cross-modal contrastive learning. Observations from multiple views are lifted and fused into this shared 3D space, where geometric structure, visual appearance, and human-centric semantic cues are jointly encoded at the instance level. We further introduce a spatial contrastive learning strategy that aligns 3D features corresponding to the same human instance across different views and modalities while separating different instances. This enables correspondence reasoning, semantic aggregation, and instance discrimination to be performed natively in 3D, improving cross-view consistency and robustness under severe occlusions. Finally, structured human body models are recovered in a feed-forward manner by regressing SMPL parameters from instance-level 3D human tokens. Extensive experiments demonstrate robust, accurate, and efficient multi-view human reconstruction in challenging real-world scenarios.

Abstract

Explore similar work

Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation

HARMONI: Aligning Human and Scene Priors for Multi-View 4D Reconstruction

Unconstrained Multi-view Human Pose Estimation with Algebraic Priors