SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion

Junjie Hu, Hujun Bao, Guofeng Zhang, Jiarui Hu, Xiyue Guo

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Abstract

Figure 1. SGFormer, which adopts satellite-ground cooperative fusion, can achieve state-of-the-art performance in scene completion and semantic prediction. Benefiting from informative satellite images and a well-designed dual-branch pipeline, SGFormer can effectively improve semantic prediction accuracy and solve the long-standing visual occlusion bottleneck suffered by purely ground-view methods.

For agents

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

get_harvested_code_for_paper("2503.16825")
get_code_for_paper("2503.16825")
have("2503.16825")

Connect an agent — have() is free.