Our complete approach, 4DHumans, achieves state-of-the-art results for tracking people from monocular video. Furthermore, we demonstrate the effectiveness of HMR 2.0 on the downstream task of action recognition, achieving significant improvements over previous pose-based action recognition approaches.

2023年5月31日 · Our complete approach, 4DHumans, achieves state-of-the-art results for tracking people from monocular video. Furthermore, we demonstrate the effectiveness of HMR 2.0 on the downstream task of action recognition, achieving significant improvements over previous pose-based action recognition approaches.

Given a reference image, SMPL sequences and camera parameters, our method is capable of generating free-view dynamic human videos. The pipeline of Human4DiT. our framework is based on 4D diffusion transformer, which adopts a cascaded structure consisting of the 2D image, the view transformer, and the temporal blocks.

We present ZeroHSI, a novel approach that enables zero-shot 4D human-scene interaction synthesis by integrating video generation and neural human rendering.

Our complete approach, 4DHumans, achieves state-of-the-art results for tracking people from monocular video. Furthermore, we demonstrate the effectiveness of HMR 2.0 on the downstream task of action recognition, achieving significant improvements over previous pose-based action recognition approaches.

4D-Humans 开源仓库是论文 Humans in 4D: Reconstructing and Tracking Humans with Transformers 的代码仓库， 实现了对人体 进行了 4D 跟踪和建模 。 4D 即四个维度，除了 我们常说的三维空间外，同时 还 涵盖了时间维度。

4DHumans: Reconstructing and Tracking Humans with Transformers - shubham-goel/4D-Humans

2024年12月24日 · We present ZeroHSI, a novel approach that enables zero-shot 4D human-scene interaction synthesis by integrating video generation and neural human rendering.

2024年5月27日 · We present a novel approach for generating 360-degree high-quality, spatio-temporally coherent human videos from a single image. Our framework combines the strengths of diffusion transformers for capturing global correlations across viewpoints and time, and CNNs for accurate condition injection.

Digital Human Resource: 2D/3D/4D Human Modeling, Avatar Generation & Animation, Clothed People Digitalization, Virtual Try-On, and Others.