This paper aims to address the challenge of reconstructing long volumetric videos from multi-view RGB videos. Recent dynamic view synthesis methods leverage powerful 4D representations, like feature grids or point cloud sequences, to achieve high-quality rendering results. However, they are typically limited to short (1~2s) video clips and often suffer from large memory footprints when dealing with longer videos. To solve this issue, we propose a novel 4D representation, named Temporal Gaussian Hierarchy, to compactly model long volumetric videos. Our key observation is that there are generally various degrees of temporal redundancy in dynamic scenes, which consist of areas changing at different speeds. Motivated by this, our approach builds a multi-level hierarchy of 4D Gaussian primitives, where each level separately describes scene regions with different degrees of content change, and adaptively shares Gaussian primitives to represent unchanged scene content over different temporal segments, thus effectively reducing the number of Gaussian primitives. In addition, the tree-like structure of the Gaussian hierarchy allows us to efficiently represent the scene at a particular moment with a subset of Gaussian primitives, leading to nearly constant GPU memory usage during the training or rendering regardless of the video length. Moreover, we design a Compact Appearance Model that mixes diffuse and view-dependent Gaussians to further minimize the model size while maintaining the rendering quality. We also develop a rasterization pipeline of Gaussian primitives based on the hardware-accelerated technique to improve rendering speed. Extensive experimental results demonstrate the superiority of our method over alternative methods in terms of training cost, rendering speed, and storage usage. To our knowledge, this work is the first approach capable of efficiently handling hours of volumetric video data while maintaining state-of-the-art rendering quality.

This paper addresses the challenging task of reconstructing the poses of multiple individuals engaged in close interactions, captured by multiple calibrated cameras. The difficulty arises from the noisy or false 2D keypoint detections due to inter-person occlusion, the heavy ambiguity in associating keypoints to individuals due to the close interactions, and the scarcity of training data as collecting and annotating motion data in crowded scenes is resource-intensive. We introduce a novel system to address these challenges. Our system integrates a learning-based pose estimation component and its corresponding training and inference strategies. The pose estimation component takes multi-view 2D keypoint heatmaps as input and reconstructs the pose of each individual using a 3D conditional volumetric network. As the network doesn't need images as input, we can leverage known camera parameters from test scenes and a large quantity of existing motion capture data to synthesize massive training data that mimics the real data distribution in test scenes. Extensive experiments demonstrate that our approach significantly surpasses previous approaches in terms of pose accuracy and is generalizable across various camera setups and population sizes. The code is available on our project page: https://github.com/zju3dv/CloseMoCap.