Pascal Fua, Mathieu Salzmann, Siddhartha Chaudhuri, Vladimir Kim, Noam Aigerman, Jan Bednarik, Shaifali Parashar
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. Temporally-coherent reconstruction and correspondences predicted by our approach (OUR), compared with other atlasbased ones -AtlasNet [19] (AN), and Differential Surface Representation [7] (DSR). Left: The reconstructed surfaces, textured with a consistent texture to visualize the correspondences between the surfaces. Middle and Right: deviations visualized using a colormap (middle) and a heatmap (right). The competing methods exhibit artifacts and wrong correspondences, while OUR yields reconstructions close to the GT. The black arrows point to inconsistencies, which are absent from our results.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.06950")
get_code_for_paper("2104.06950")
have("2104.06950")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.06950.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.06950)
Connect an agent — have() is free.