We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose 4 insights that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image. These insights are: (1) denoise the "ground truth" surface normals in the training set to ensure consistency with the semantic labels; (2) concurrently train on a mix of real and synthetic data, instead of pretraining on synthetic and finetuning on real; (3) jointly predict normals and semantics using a shared model, but only backpropagate errors on pixels that have valid training labels; (4) slim down the model and use grayscale instead of color inputs. Despite the simplicity of these steps, we demonstrate consistently improved results on several datasets, using a model that runs at 12 fps on a standard mobile phone.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1906.06792")
get_code_for_paper("1906.06792")
have("1906.06792")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1906.06792.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1906.06792)
Connect an agent — have() is free.