Semantic segmentation models struggle to generalize in the presence of domain shift.
To enable this, we develop a GAN-tuned physics-based noise model to more accurately represent camera noise at the lowest light levels.
Our key insight is that by reasoning on how implicit field perturbations impact local surface geometry, one can ultimately differentiate the 3D location of surface samples with respect to the underlying deep implicit field.
We confirm the benefits of our contributions in controlled experiments and report substantial gains in stability and realism in comparison to recent image-to-image translation methods and a variety of other baselines.
Unfortunately, these methods are often not suitable for applications that require an explicit mesh-based surface representation because converting an implicit field to such a representation relies on the Marching Cubes algorithm, which cannot be differentiated with respect to the underlying implicit field.
Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research.
Ranked #1 on 3D Reconstruction on 300W
We scale this baseline to higher resolutions by proposing a memory-efficient shape encoding, which recursively decomposes a 3D shape into nested shape layers, similar to the pieces of a Matryoshka doll.
Ranked #4 on 3D Object Reconstruction on Data3D−R2N2