paper-with-me

홈 › Papers

Rendering Multi-Human and Multi-Object with 3D Gaussian Splatting

2026-04-03 · Weiquan Wang, Jun Xiao, Feifei Shao, Yi Yang, Yueting Zhuang, Long Chen arxiv

Reconstructing dynamic scenes with multiple interacting humans and objects from sparse-view inputs is a critical yet challenging task, essential for creating high-fidelity digital twins for robotics and VR/AR. This problem, which we term Multi-Human Multi-Object (MHMO) rendering, presents two significant obstacles: achieving view-consistent representations for individual instances under severe mutual occlusion, and explicitly modeling the complex and combinatorial dependencies that arise from their interactions. To overcome these challenges, we propose MM-GS, a novel hierarchical framework built upon 3D Gaussian Splatting. Our method first employs a Per-Instance Multi-View Fusion module to establish a robust and consistent representation for each instance by aggregating visual information across all available views. Subsequently, a Scene-Level Instance Interaction module operates on a global scene graph to reason about relationships between all participants, refining their attributes to capture subtle interaction effects. Extensive experiments on challenging datasets demonstrate that our method significantly outperforms strong baselines, producing state-of-the-art results with high-fidelity details and plausible inter-instance contacts.

📄 PDF Abstract BibTeX arXiv:2604.02996

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GASPACHO: Gaussian Splatting for Controllable Humans and Objects

2025-03-12 · Aymen Mir, Arthur Moreau, Helisa Dhamo, Zhensong Zhang 외

We present GASPACHO: a method for generating photorealistic controllable renderings of human-object interactions. Given a set of multi-view RGB images of human-object interactions, our method reconstructs animatable temp…

Human-Object Interaction DetectionObject

Generalizable Human Gaussians for Sparse View Synthesis

2024-07-17 · Youngjoong Kwon, Baole Fang, Yixing Lu, Haoye Dong 외

Recent progress in neural rendering has brought forth pioneering methods, such as NeRF and Gaussian Splatting, which revolutionize view rendering across various domains like AR/VR, gaming, and content creation. While the…

NeRFNeural Rendering

UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modeling

2024-03-18 · Yujiao Jiang, Qingmin Liao, Xiaoyu Li, Li Ma 외

Reconstructing photo-realistic drivable human avatars from multi-view image sequences has been a popular and challenging topic in the field of computer vision and graphics. While existing NeRF-based methods can achieve h…

NeRF

Memorize What Matters: Emergent Scene Decomposition from Multitraverse

2024-05-27 · Yiming Li, Zehong Wang, Yue Wang, Zhiding Yu 외

Humans naturally retain memories of permanent elements, while ephemeral moments often slip through the cracks of memory. This selective retention is crucial for robotic perception, localization, and mapping. To endow rob…

3D ReconstructionNeural RenderingSegmentationSemantic Segmentation

Robust Multi-Object 4D Generation for In-the-wild Videos

2025-01-01 · CVPR 2025 1 · Wen-Hsuan Chu, Lei Ke, Jianmeng Liu, Mingxiao Huo 외

We address the challenge of generating dynamic 4D scenes from monocular multi-object videos with heavy occlusions and introduce Robust4DGen, a novel approach that integrates rendering-based deformable 3D Gaussian opt…

ObjectScene Generation