OrienPose：方向引导的新视角合成用于单图像未见物体姿态估计
OrienPose: Orientation-Guided Novel View Synthesis for Single-Image Unseen Object Pose Estimation
论文将方向线索显式注入参考视图的潜变量嵌入，并用几何层面的方向一致性损失监督视角变换，这为基于新视角合成的物体姿态估计提供了可复用的几何约束思路，能提升模板匹配的可靠性。
原文依据 we introduce the Orientation-Aware Guidance, which explicitly injects object orientation cues into the reference latent embedding
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从单张图像估计未见物体的三维姿态仍然是计算机视觉中一个基础而具有挑战性的问题，尤其是在无 CAD 模型的设定下。开创性的尝试通过匹配由新视角合成（NVS）生成的模板来解决该问题，其本质是学习从参考视图到目标视图的几何变换。尽管这些方法有前景，但由于起始方向未定义，它们只能在像素级监督下近似该变换。在缺乏显式几何约束来验证预测变换正确性的情况下，现有方法常常合成出几何结构扭曲或局部纹理严重模糊的新视角，导致模板匹配不可靠且姿态估计结果次优。为此，我们提出 OrienPose，一种通过方向感知的新视角合成从单张图像进行物体姿态估计的新框架。具体而言，我们引入方向感知引导，将物体方向线索显式注入参考潜变量嵌入中，以增强视角变换过程中的方向感知。我们还引入方向一致性损失，在几何层面监督视角变换，从而在像素级相似度之外建立充分的监督，提供显式且几何一致的变换引导。该损失使得估计参考方向而非使用其真实姿态成为合理选择，从而确保注入先验与监督先验之间的坐标域对齐。大量实验表明，OrienPose 在单视图未见物体姿态估计中达到最优性能，并对图像退化表现出令人印象深刻的鲁棒性。我们的代码可在 https://github.com/pubyLu/OrienPose 获取。
英文原文摘要 1840 字符
Estimating the 3D pose of unseen objects from a single image remains a fundamental yet challenging problem in computer vision, especially under a CAD model-free setting.Pioneering attempts address this issue by matching templates generated through Novel View Synthesis (NVS), which essentially aims to learn the geometric transformation from a reference to a target view. While promising, these methods can only approximate this transformation under pixel-level supervision, as the starting orientation remains undefined. In the absence of explicit geometric constraints to verify the correctness of the predicted transformation, existing methods often synthesize novel views with geometry-distorted structures or severely blurred local textures, leading to unreliable template matching and suboptimal pose estimation results. To this end, we propose OrienPose, a novel object pose estimation framework via orientation-aware NVS from a single image. Specifically, we introduce the Orientation-Aware Guidance, which explicitly injects object orientation cues into the reference latent embedding to enhance orientation awareness during viewpoint transformation. We also introduce an orientation consistency loss that supervises viewpoint transformation at the geometric level, establishing sufficient supervision for explicit and geometry-consistent transformation guidance beyond pixel-level similarity. This loss justifies estimating the reference orientation rather than using its ground-truth pose, thereby ensuring the alignment of coordinate domains between the injected and supervised priors. Extensive experiments demonstrate that OrienPose achieves state-of-the-art performance in single-view unseen object pose estimation and impressive robustness to image degradations. Our code is available at https://github.com/pubyLu/OrienPose.