Metraipolis › archive › dc_f623d4a79f16

Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation — arXiv:2609.00745

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00745
License (as archived)
CC0-1.0
Archived
2026-10-17T07:13:36.237Z
SHA-256 of the archived text
633a2c6b00f685ad0cc7d1c65acbfbba0b3a951ec7c0924118551419c05f7dfd
Stable URL of this page
https://metraipolis.com/documento/dc_f623d4a79f16

How to cite

Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation — arXiv:2609.00745 — arXiv (en), https://arxiv.org/abs/2609.00745 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f623d4a79f16 (Metraipolis archive dc_f623d4a79f16, sha256 633a2c6b00f685ad0cc7d1c65acbfbba0b3a951ec7c0924118551419c05f7dfd)
BibTeX
@misc{dcf623d4a79f16,
  title = {Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation — arXiv:2609.00745},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00745},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f623d4a79f16; sha256 633a2c6b00f685ad0cc7d1c65acbfbba0b3a951ec7c0924118551419c05f7dfd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00745. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.00745 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:00:58.929Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).