Learning Category-Specific Mesh Reconstruction from Image Collections

Angjoo Kanazawa, Shubham Tulsiani, Alexei A. Efros, Jitendra Malik; The European Conference on Computer Vision (ECCV), 2018, pp. 371-386


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 category where a shape is parameterized by a learned mean shape and per-instance predicted deformation. Our approach allows leveraging an annotated image collection for training, where the deformable model and the 3D prediction mechanism are learned without relying on ground-truth 3D or multi-view supervision. Our representation enables us to go beyond existing 3D prediction approaches by incorporating texture inference as prediction of an image in a canonical appearance space. Additionally, we show that semantic keypoints can be easily associated with the predicted shapes. We present qualitative and quantitative results of our approach on CUB and PASCAL3D datasets and show that we can learn to predict diverse shapes and textures across birds using only annotated image collections. The project website can be found at https://akanazawa.github.io/cmr/.

Related Material

author = {Kanazawa, Angjoo and Tulsiani, Shubham and Efros, Alexei A. and Malik, Jitendra},
title = {Learning Category-Specific Mesh Reconstruction from Image Collections},
booktitle = {The European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}