Timezone: »

Equivariant Neural Rendering
Emilien Dupont · Miguel Angel Bautista Martin · Alex Colburn · Aditya Sankar · Joshua M Susskind · Qi Shan

Wed Jul 15 12:00 PM -- 12:45 PM & Thu Jul 16 01:00 AM -- 01:45 AM (PDT) @

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 equivariance of the scene representation with respect to 3D transformations. Our formulation allows us to infer and render scenes in real time while achieving comparable results to models requiring minutes for inference. In addition, we introduce two challenging new datasets for scene representation and neural rendering, including scenes with complex lighting and backgrounds. Through experiments, we show that our model achieves compelling results on these datasets as well as on standard ShapeNet benchmarks.

Author Information

Emilien Dupont (University of Oxford)
Miguel Angel Bautista Martin (Apple Inc.)
Alex Colburn (Apple Inc.)
Aditya Sankar (Apple Inc.)
Joshua M Susskind (Apple, Inc.)
Qi Shan (Apple Inc)

More from the Same Authors