GazeOnce360：基于鱼眼相机的360度多人视线估计与全局-局部特征融合
GazeOnce360: Fisheye-Based 360deg Multi-Person Gaze Estimation with Global-Local Feature Fusion
把鱼眼畸变下的多人视线估计形式化为一个端到端任务，并用旋转卷积加眼部关键点监督来对抗畸变，再用全局低分辨率与局部高分辨率眼部区域的双分辨率融合保留细粒度眼睛特征；做鱼眼/广角相机下的人体或人脸分析时，这套畸变感知卷积与局部高分辨率裁剪融合可直接复用。
原文依据 incorporating rotational convolutions and eye landmark supervision
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 GazeOnce360，一种新颖的端到端模型，用于从单台桌面安装的朝上鱼眼相机进行多人视线估计。与依赖前向相机、受限于特定视角的传统方法不同，我们研究了一个此前较少被探索的设定：从朝上的鱼眼视角估计分布在 360 度场景中的多人的三维视线方向。为支持该设定下的研究，我们引入了 MPSGaze360，一个使用 Unreal Engine 渲染的大规模合成数据集，包含多样的多人配置以及精确的三维视线与眼部关键点标注。我们的模型通过引入旋转卷积与眼部关键点监督，应对鱼眼图像固有的严重畸变与视角变化。为更好地捕捉对视线估计至关重要的细粒度眼部特征，我们提出一种双分辨率架构，将全局低分辨率上下文与高分辨率局部眼部区域相融合。实验结果验证了模型中各组成部分的有效性。本工作凸显了基于鱼眼的 360 度视线估计在实际多人场景中的可行性与潜力。项目主页：https://caizhuojiang.github.io/GazeOnce360/。
英文原文摘要 1251 字符
We present GazeOnce360, a novel end-to-end model for multi-person gaze estimation from a single tabletop-mounted upward-facing fisheye camera. Unlike conventional approaches that rely on forward-facing cameras in constrained viewpoints, we address the underexplored setting of estimating the 3D gaze direction of multiple people distributed across a 360deg scene from an upward fisheye perspective. To support research in this setting, we introduce MPSGaze360, a large-scale synthetic dataset rendered using Unreal Engine, featuring diverse multi-person configurations with accurate 3D gaze and eye landmark annotations. Our model tackles the severe distortion and perspective variation inherent in fisheye imagery by incorporating rotational convolutions and eye landmark supervision. To better capture fine-grained eye features crucial for gaze estimation, we propose a dual-resolution architecture that fuses global low-resolution context with high-resolution local eye regions. Experimental results demonstrate the effectiveness of each component in our model. This work highlights the feasibility and potential of fisheye-based 360deg gaze estimation in practical multi-person scenarios. Project page: https://caizhuojiang.github.io/GazeOnce360/.