SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.11744 · 2020

End-to-End Optimization of Scene Layout

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
aluo-x/3D_SLN canonical 8 of 10
FunctionStatusWhere it lives
calculate_model_losses Ran aluo-x/3D_SLN/utils.py
code served (permissive licence) · get_code("5177de12ba6d4684")
compute_rel Ran aluo-x/3D_SLN/utils.py
code served (permissive licence) · get_code("314bf1bcea60acb0")
get_nonspade_norm_layer Ran aluo-x/3D_SLN/models/SPADE_related.py
code served (permissive licence) · get_code("130906eb042774b8")
load_json Ran aluo-x/3D_SLN/models/misc.py
code served (permissive licence) · get_code("095a900bebc6eb1e")
load_json Ran aluo-x/3D_SLN/render/render_caller.py
code served (permissive licence) · get_code("2c077e742f417c7c")
make_mlp Ran aluo-x/3D_SLN/models/graph.py
code served (permissive licence) · get_code("dd4fe4836e5846da")
padded_conv Ran aluo-x/3D_SLN/models/SPADE_related.py
code served (permissive licence) · get_code("3649b4be81ae0915")
save_pkl Ran aluo-x/3D_SLN/models/diff_render.py
code served (permissive licence) · get_code("7a9aecca4b95627c")
get_cam_mat Not yet run aluo-x/3D_SLN/models/diff_render.py
code served (permissive licence) · get_code("bae85abff818557f")
mesh_render_func Not yet run aluo-x/3D_SLN/models/diff_render.py
code served (permissive licence) · get_code("fa02c91e2967d067")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose an end-to-end variational generative model for scene layout synthesis conditioned on scene graphs. Unlike unconditional scene layout generation, we use scene graphs as an abstract but general representation to guide the synthesis of diverse scene layouts that satisfy relationships included in the scene graph. This gives rise to more flexible control over the synthesis process, allowing various forms of inputs such as scene layouts extracted from sentences or inferred from a single color image. Using our conditional layout synthesizer, we can generate various layouts that share the same structure of the input example. In addition to this conditional generation design, we also integrate a differentiable rendering module that enables layout refinement using only 2D projections of the scene. Given a depth and a semantics map, the differentiable rendering module enables optimizing over the synthesized layout to fit the given input in an analysis-by-synthesis fashion. Experiments suggest that our model achieves higher accuracy and diversity in conditional scene synthesis and allows exemplar-based scene generation from various input forms.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2007.11744")
get_code_for_paper("2007.11744")
have("2007.11744")

Connect an agent — have() is free.