Zero-Shot Monocular Scene Flow Estimation in the Wild

Figure 1. Our model for monocular scene flow estimation predicts accurate pointmaps and 3D offsets for dynamic scenes from two input images (shown below each pane) captured by two cameras C1 and C2 at times t1 an t2, respectively. The image shows an interpolation of the pointmaps from C1 at t1 to C2 at t2. These examples are from datasets not seen in training, showcasing the strong generalization abilities of our method.