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

• URL: http://arxiv.org/abs/2609.00745v1
• Date: Tue, 01 Sep 2026 05:24:20 GMT
• Title: Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation
• Abstract summary: We propose a new top-down paradigm that maintains a unified, instance-centric human-aware 3D space.<n>Cross-modal contrastive learning enables simultaneous camera calibration, cross-view association, and human reconstruction.<n>Experiments demonstrate robust, accurate, and efficient multi-view human reconstruction in challenging real-world scenarios.
• Score: 12.32801567231421
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation [58.47973015036709]
  DisPOSE is a self-supervised framework that approximates the inherently discrete multi-view person-assignment problem.<n>By employing differentiable Sinkhorn projections during denoising, our model learns to guide solutions toward valid and feasible assignments.<n>The proposed approach outperforms current state-of-the-art self-supervised methods on standard datasets.
  arXiv  Detail & Related papers  (2026-06-05T16:14:39Z)
• AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors [81.50960055126156]
  We present textbfAHAP, a feed-forward framework for reconstructing arbitrary humans from arbitrary camera perspectives.<n>Our core lies in the effective fusion of multi-view geometry to assist human association, reconstruction and localization.<n>A Human Head fuses cross-view features and scene context for SMPL prediction, guided by cross-view reprojection losses to enforce body pose consistency.
  arXiv  Detail & Related papers  (2026-02-27T11:53:45Z)
• InpaintHuman: Reconstructing Occluded Humans with Multi-Scale UV Mapping and Identity-Preserving Diffusion Inpainting [64.42884719282323]
  InpaintHuman is a novel method for generating high-fidelity, complete, and animatable avatars from occluded monocular videos.<n>Our approach employs direct pixel-level supervision to ensure identity fidelity.
  arXiv  Detail & Related papers  (2026-01-05T13:26:02Z)
• HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation [51.27178551863772]
  We propose a unified framework that enables the joint modeling of appearance and human-part semantics from a single image.<n>HumanCrafter surpasses existing state-of-the-art methods in both 3D human-part segmentation and 3D human reconstruction from a single image.
  arXiv  Detail & Related papers  (2025-11-01T09:29:36Z)
• CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image [37.16845070245751]
  We present a novel pipeline to reconstruct 3D humans with multiview consistency from a single occluded image.<n>A 3D reconstruction model is then trained to predict a set of 3D Gaussians conditioned on both the occluded input and synthesized views.<n> achieves significant improvements in terms of both novel view synthesis (upto 3 db PSNR) and geometric reconstruction under challenging conditions.
  arXiv  Detail & Related papers  (2025-03-19T19:56:18Z)
• Progressive Multi-view Human Mesh Recovery with Self-Supervision [68.60019434498703]
  Existing solutions typically suffer from poor generalization performance to new settings. We propose a novel simulation-based training pipeline for multi-view human mesh recovery.
  arXiv  Detail & Related papers  (2022-12-10T06:28:29Z)
• Multi-person Implicit Reconstruction from a Single Image [37.6877421030774]
  We present a new end-to-end learning framework to obtain detailed and spatially coherent reconstructions of multiple people from a single image. Existing multi-person methods suffer from two main drawbacks: they are often model-based and cannot capture accurate 3D models of people with loose clothing and hair.
  arXiv  Detail & Related papers  (2021-04-19T13:21:55Z)
• HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation [54.23770284299979]
  This paper introduces a novel form of supervision - Hierarchical Multi-person Ordinal Relations (HMOR) HMOR encodes interaction information as the ordinal relations of depths and angles hierarchically. An integrated top-down model is designed to leverage these ordinal relations in the learning process. The proposed method significantly outperforms state-of-the-art methods on publicly available multi-person 3D pose datasets.
  arXiv  Detail & Related papers  (2020-08-01T07:53:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.