Dahua Lin, Xiao Fu, Ping Tan, Wei Yin, Shaojie Shen, Yuexin Ma, Xiaoxiao Long, Kaixuan Wang, Mu Hu
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.
https://fuxiao0719.github.io/projects/geowizard/ 1 CUHK 2 The University of Adelaide 3 HKUST 4 ShanghaiTech University 5 HKU 6 Light Illusions 3D Reconstruction Depth/Normal Guided Image Generation * Equal contribution Fu. et al. improve generalization, detail preservation, and efficiency in resource usage. Specifically, we extend the original stable diffusion model to jointly predict depth and normal, allowing mutual information exchange and high consistency between the two representations. More importantly, we propose a simple yet effective strategy to segregate the complex data distribution of various scenes into distinct sub-distributions. This strategy enables our model to recognize different scene layouts, capturing 3D geometry with remarkable fidelity. GeoWizard sets new benchmarks for zero-shot depth and normal prediction, significantly enhancing many downstream applications such as 3D reconstruction, 2D content creation, and novel viewpoint synthesis.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.12013")
get_code_for_paper("2403.12013")
have("2403.12013")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2403.12013.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2403.12013)
Connect an agent — have() is free.