26 papers with code • 4 benchmarks • 4 datasets
Despite the recent progress of generative adversarial networks (GANs) at synthesizing photo-realistic images, producing complex urban scenes remains a challenging problem.
Moreover, object representations are often inferred using RNNs which do not scale well to large images or iterative refinement which avoids imposing an unnatural ordering on objects in an image but requires the a priori initialisation of a fixed number of object representations.
Ranked #1 on Unsupervised Object Segmentation on ObjectsRoom
In this paper, we introduce Generative Scene Networks (GSN), which learns to decompose scenes into a collection of many local radiance fields that can be rendered from a free moving camera.
Ranked #1 on Scene Generation on VizDoom
In contrast, we do not use any appearance information, and implicitly learn object relations using the self-attention mechanism of transformers.
We have witnessed rapid progress on 3D-aware image synthesis, leveraging recent advances in generative visual models and neural rendering.
Ranked #3 on Scene Generation on VizDoom
We present a conceptually simple but effective funnel activation for image recognition tasks, called Funnel activation (FReLU), that extends ReLU and PReLU to a 2D activation by adding a negligible overhead of spatial condition.
Ranked #1 on Scene Generation on 10 Monkey Species
In contrast to voxel-based representations, radiance fields are not confined to a coarse discretization of the 3D space, yet allow for disentangling camera and scene properties while degrading gracefully in the presence of reconstruction ambiguity.
Ranked #2 on Scene Generation on VizDoom
We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects.