Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency

April 20, 2017 · Entered Twilight · 🏛 Computer Vision and Pattern Recognition

"No code URL or promise found in abstract"
"Derived repo from GitHub Pages (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, README.md, benchmark, cachedir, data, demo, docs, drcLoss, experiments, nnutils, preprocess, rayUtils, utils

Authors Shubham Tulsiani, Tinghui Zhou, Alexei A. Efros, Jitendra Malik arXiv ID 1704.06254 Category cs.CV: Computer Vision Citations 581 Venue Computer Vision and Pattern Recognition Repository https://github.com/shubhtuls/drc ⭐ 160 Last Checked 12 days ago

Abstract

We study the notion of consistency between a 3D shape and a 2D observation and propose a differentiable formulation which allows computing gradients of the 3D shape given an observation from an arbitrary view. We do so by reformulating view consistency using a differentiable ray consistency (DRC) term. We show that this formulation can be incorporated in a learning framework to leverage different types of multi-view observations e.g. foreground masks, depth, color images, semantics etc. as supervision for learning single-view 3D prediction. We present empirical analysis of our technique in a controlled setting. We also show that this approach allows us to improve over existing techniques for single-view reconstruction of objects from the PASCAL VOC dataset.