3D Morphable Models (3DMMs) are statistical modelsthat represent facial texture and shape variations using a setof linear bases and more particular Principal ComponentAnalysis (PCA). 3DMMs were used as statistical priors forreconstructing 3D faces from images by solving non-linearleast square optimization problems. Recently, 3DMMs wereused as generative models for training non-linear mappings(i.e., regressors) from image to the parameters of the modelsvia Deep Convolutional Neural Networks (DCNNs). Nev-ertheless, all of the above methods use either fully con-nected layers or 2D convolutions on parametric unwrappedUV spaces leading to large networks with many parame-ters. In this paper, we present the first, to the best of ourknowledge, non-linear 3DMMs by learning joint textureand shape auto-encoders using direct mesh convolutions.We demonstrate how these auto-encoders can be used totrain very light-weight models that perform Coloured MeshDecoding (CMD) in-the-wild at a speed of over 2500 FPS.