Dan Xu, Hanrong Ye
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.
Figure 1: TaskPrompter, trained on Cityscapes-3D, is able to simultaneously generate predictions for various 2D and 3D scene understanding tasks, such as monocular 3D vehicle detection, semantic segmentation, and monocular depth estimation (video link).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2304.00971")
get_code_for_paper("2304.00971")
have("2304.00971")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2304.00971.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2304.00971)
Connect an agent — have() is free.