SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data
This addresses the problem of reducing labeling effort and noise in human pose estimation for computer vision applications, though it is incremental as it builds on existing domain-adaptation techniques.
The paper tackled learning dense 2.5D and 3D human pose representations from simulated data, achieving state-of-the-art performance on the DensePose MSCOCO benchmark by outperforming methods trained on real labeled images.
With a proliferation of generic domain-adaptation approaches, we report a simple yet effective technique for learning difficult per-pixel 2.5D and 3D regression representations of articulated people. We obtained strong sim-to-real domain generalization for the 2.5D DensePose estimation task and the 3D human surface normal estimation task. On the multi-person DensePose MSCOCO benchmark, our approach outperforms the state-of-the-art methods which are trained on real images that are densely labelled. This is an important result since obtaining human manifold's intrinsic uv coordinates on real images is time consuming and prone to labeling noise. Additionally, we present our model's 3D surface normal predictions on the MSCOCO dataset that lacks any real 3D surface normal labels. The key to our approach is to mitigate the "Inter-domain Covariate Shift" with a carefully selected training batch from a mixture of domain samples, a deep batch-normalized residual network, and a modified multi-task learning objective. Our approach is complementary to existing domain-adaptation techniques and can be applied to other dense per-pixel pose estimation problems.