Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation

A great example of how domain-specific knowledge can help design network architecture, in this case helping them make the jump from supervised learning (where training data may be difficult or time-consuming to acquire) to unsupervised learning (where training data is often plentiful). Modern 3D human pose estimation techniques rely on deep networks, which require large…Read More

Deep Unsupervised Intrinsic Image Decomposition by Siamese Training

Intrinsic image decomposition means splitting the observed color of a scene into its underlying components, such as illumination and reflectance. Once this process has been performed the layers can be manipulated independently before being recomposed to recreate a modified scene. What’s particularly interesting about this work is that it uses unsupervised training, which by definition…Read More

Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation

Although this technique to estimate camera motion and decompose the scene into rigid/dynamic motion (a potential aid to segmentation) relies on a depth channel in the input images, it may not be long until new approaches are developed which can operate on RGB only. Estimation of 3D motion in a dynamic scene from a temporal…Read More

Learning Category-Specific Mesh Reconstruction from Image Collections

Some truly remarkable results given the dataset from which this model was trained. Code on github will be available in the future. We present a learning framework for recovering the 3D shape, camera, and texture of an object from a single image. The shape is represented as a deformable 3D mesh model of an object…Read More