We present a novel technique to estimate the 6D pose of objects from single images where the 3D geometry of the object is only given approximately and not as a precise 3D model. To achieve this, we employ a dense 2D-to-3D correspondence predictor that regresses 3D model coordinates for every pixel. In addition to the 3D coordinates, our model also estimates the pixel-wise coordinate error to discard correspondences that are likely wrong. This allows us to generate multiple 6D pose hypotheses of the object, which we then refine iteratively using a highly efficient region-based approach. We also introduce a novel pixel-wise posterior formulation by which we can estimate the probability for each hypothesis and select the most likely one. As we show in experiments, our approach is capable of dealing with extreme visual conditions including overexposure, high contrast, or low signal-to-noise ratio. This makes it a powerful technique for the particularly challenging task of estimating the pose of tumbling satellites for in-orbit robotic applications. Our method achieves state-of-the-art performance on the SPEED+ dataset and has won the SPEC2021 post-mortem competition.

翻译：我们提出了一种新颖技术，用于从单张图像估计物体的六自由度姿态，其中物体的三维几何形状仅以近似形式给出，而非精确的三维模型。为实现这一目标，我们采用密集的二维到三维对应关系预测器，为每个像素回归出三维模型坐标。除三维坐标外，我们的模型还估计像素级坐标误差，以剔除可能错误的对应关系。这使我们能够生成多个物体的六自由度姿态假设，随后通过高效的区域基方法对这些假设进行迭代优化。我们还引入了一种新颖的像素级后验公式，能够估计每个假设的概率并选择最可能的姿态。实验表明，我们的方法能够处理极端视觉条件，包括过度曝光、高对比度或低信噪比场景。这使得它成为轨道机器人应用中翻滚卫星姿态估计这一极具挑战性任务的强大技术。我们的方法在SPEED+数据集上达到了最先进性能，并赢得了SPEC2021事后竞赛冠军。