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

arXiv: https://arxiv.org/abs/2609.00745 · HTML: https://mlsanity.com/paper/2609.00745/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 29 of 29)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views](https://mlsanity.com/paper/2505.23716/) (2025)
- [Monocular, One-stage, Regression of Multiple 3D People](https://mlsanity.com/paper/2008.12272/) (2020)
- [MUSt3R: Multi-view Network for Stereo 3D Reconstruction](https://mlsanity.com/paper/2503.01661/) (2025)
- [Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot](https://mlsanity.com/paper/2402.14654/) (2024)
- [SHERF: Generalizable Human NeRF from a Single Image](https://mlsanity.com/paper/2303.12791/) (2023)
- [Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors](https://mlsanity.com/paper/2503.17316/) (2025)
- [Direct Multi-view Multi-person 3D Pose Estimation](https://mlsanity.com/paper/2111.04076/) (2021)
- [EgoHumans: An Egocentric 3D Multi-Human Benchmark](https://mlsanity.com/paper/2305.16487/) (2023)
- [Light3R-SfM: Towards Feed-forward Structure-from-Motion](https://mlsanity.com/paper/2501.14914/) (2025)
- [VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild](https://mlsanity.com/paper/2108.02452/) (2021)
- [Human3R: Everyone Everywhere All at Once](https://mlsanity.com/paper/2510.06219/) (2025)
- [Reconstructing People, Places, and Cameras](https://mlsanity.com/paper/2412.17806/) (2024)
- [Joint Optimization for 4D Human-Scene Reconstruction in the Wild](https://mlsanity.com/paper/2501.02158/) (2025)
- [Synergistic Global-space Camera and Human Reconstruction from Videos](https://mlsanity.com/paper/2405.14855/) (2024)
- [Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior](https://mlsanity.com/paper/2207.05375/) (2022)
- [HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction](https://mlsanity.com/paper/2508.16433/) (2025)
- [Regist3R: Incremental Registration with Stereo Foundation Model](https://mlsanity.com/paper/2504.12356/) (2025)
- [MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation](https://mlsanity.com/paper/2509.00649/) (2025)
- [Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras](https://mlsanity.com/paper/2401.15616/) (2024)
- [Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction](https://mlsanity.com/paper/2504.13419/) (2025)
- [Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras](https://mlsanity.com/paper/2510.24464/) (2025)
- [Simultaneously Recovering Multi-Person Meshes and Multi-View Cameras with Human Semantics](https://mlsanity.com/paper/2412.18785/) (2024)

## Abstract (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.