← Search

Miguel Bautista Martin

2 accepted papers

2020

Equivariant Neural Rendering

ICML 2020poster

We propose a framework for learning neural scene representations directly from images, without 3D supervision. Our key insight is that 3D structure can be imposed by ensuring that the learned representation transforms like a real 3D scene. Specifically, we introduce a loss which enforces equivarianc…

Cited by 77SourcePDFScholar
2019

Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment

ICML 2019oral

In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to directly optimize the evaluation metric. We propose a sample e…

Cited by 99SourcePDFScholar