P Narayanan, Vinayak Gupta, Rahul Goel, Sirikonda Dhawal
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.
Traditional Radiance Field (RF) representations capture details of a specific scene and must be trained afresh on each scene. Semantic feature fields have been added to RFs to facilitate several segmentation tasks. Generalised RF representations learn the principles of view interpolation. A generalised RF can render new views of an unknown and untrained scene, given a few views. We present a way to distil feature fields into the generalised GNT representation. Our GSN representation generates new views of unseen scenes on the fly along with consistent, per-pixel semantic features. This enables multi-view segmentation of arbitrary new scenes. We show different semantic features being distilled into generalised RFs. Our multi-view segmentation results are on par with methods that use traditional RFs. GSN closes the gap between standard and generalisable RF methods significantly.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.04632")
get_code_for_paper("2402.04632")
have("2402.04632")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.04632.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.04632)
Connect an agent — have() is free.