Learning camera viewpoint using CNN to improve 3D body pose estimation
This work addresses the problem of improving 3D pose accuracy for computer vision applications, but it is incremental as it builds on existing methods by adding viewpoint estimation.
The paper tackled 3D human pose estimation from a single RGB image by learning camera viewpoint with a CNN, achieving up to 20% error reduction on the Human3.6m benchmark compared to state-of-the-art methods without body part segmentation.
The objective of this work is to estimate 3D human pose from a single RGB image. Extracting image representations which incorporate both spatial relation of body parts and their relative depth plays an essential role in accurate3D pose reconstruction. In this paper, for the first time, we show that camera viewpoint in combination to 2D joint lo-cations significantly improves 3D pose accuracy without the explicit use of perspective geometry mathematical models.To this end, we train a deep Convolutional Neural Net-work (CNN) to learn categorical camera viewpoint. To make the network robust against clothing and body shape of the subject in the image, we utilized 3D computer rendering to synthesize additional training images. We test our framework on the largest 3D pose estimation bench-mark, Human3.6m, and achieve up to 20% error reduction compared to the state-of-the-art approaches that do not use body part segmentation.