Both versions are aligned block by block, in reading order: title, the essentials, then paragraph by paragraph. Where the translation merged or split a paragraph, the matching cell stays empty — we never pair two passages by guesswork.
双手伸向工件，短暂被遮住；重新回到镜头时，系统还要接得上刚才的动作。这正是第一视角操作视频最容易丢失信息的地方。大晓机器人联合香港中文大学多媒体实验室、南洋理工大学和上海交通大学开源了ACE-Ego-Hand，可对整段视频一次分析，直接输出双手姿态、形状、可见性和3D位置，团队已产出约5000小时训练数据。
Hands reach toward a workpiece and are briefly obscured. When they return to the camera’s view, the system still needs to pick up where the previous motion left off. This is precisely where egocentric operation videos are most likely to lose information. Daxiao Robotics, together with the Multimedia Lab at the Chinese University of Hong Kong, Nanyang Technological University and Shanghai Jiao Tong University, has open-sourced ACE-Ego-Hand. The model can analyze an entire video in one pass and directly output both hands’ pose, shape, visibility and 3D positions. The team has produced about 5,000 hours of training data.
它与传统路径不同。过去的模型通常逐帧检测，或按视频窗口做时序回归，也有模型依靠多步扩散采样，逐步生成中间视频或像素结果，再估计手部姿态。ACE-Ego-Hand把视频扩散模型改造成几何编码器：输入先经过VAE压缩，模型在潜变量上进行一次前向传播，再从视频扩散Transformer模块读取时空特征，交给双向时空解码器完成输出。
Its approach differs from traditional pipelines. Earlier models typically detected hands frame by frame or performed temporal regression over video windows. Some also relied on multiple rounds of diffusion sampling to gradually generate intermediate video or pixel results before estimating hand pose. ACE-Ego-Hand converts a video diffusion model into a geometric encoder: the input first passes through a VAE for compression, the model performs a single forward pass on the latent variables, and spatiotemporal features are then read from the video diffusion Transformer module and passed to a bidirectional spatiotemporal decoder for output.
这套双向推理机制专门处理手部消失的片段。模型不使用因果掩码，不只依赖已经发生的画面，而是同时查看手部离开视野前和重新出现后的信息；前者提供运动起点、速度与方向，后者提供终点和姿态约束。相比离开画面后单向外推，这种方式旨在减少轨迹漂移，保持手部身份和运动连续。
This bidirectional reasoning mechanism is designed specifically to handle segments in which hands disappear. The model does not use a causal mask or rely only on frames that have already occurred. Instead, it examines information from both before the hand leaves the field of view and after it reappears. The former provides the motion’s starting point, speed and direction; the latter provides an endpoint and pose constraints. Compared with one-way extrapolation after a hand leaves the frame, this approach is intended to reduce trajectory drift and preserve hand identity and motion continuity.
相机变化也被纳入设计。测试时，ACE-Ego-Hand无需显式输入相机内参，也就是相机自身的几何参数；面对原生鱼眼超广角视频，它无需提前标定或做图像去畸变，而是直接从畸变画面预测像素到三维空间的观测射线，恢复手部在相机坐标系下的度量3D位置。
Camera changes are also incorporated into the design. During testing, ACE-Ego-Hand requires no explicit camera intrinsics—the camera’s own geometric parameters. For native fisheye ultra-wide-angle video, it requires neither advance calibration nor image undistortion. Instead, it directly predicts observation rays from the distorted image into 3D space and recovers the hands’ metric 3D positions in the camera coordinate system.
按团队给出的测试结果，模型在单张A100 GPU（图形处理器）上达到约63.1 fps，约为ViDiHand高精度配置的33倍；它可以服务于产线操作数据采集、机器人示教、人工装配过程分析、灵巧手动作重定向和模仿学习数据构建。
According to the team’s test results, the model reaches about 63.1 fps on a single A100 GPU (graphics processing unit), roughly 33x the speed of ViDiHand’s high-accuracy configuration. It can support production-line operation data collection, robot teaching, manual assembly process analysis, dexterous-hand motion retargeting and the creation of imitation-learning data.