Andreas Geiger, Songyou Peng, Chiyu Max, Yiyi Liao, Michael Niemeyer, Marc Pollefeys, Jiang
We lifted 7 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| autonomousvision/shape_as_points | canonical | 6 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| fftfreqs | Ran | autonomousvision/shape_as_points/src/dpsr.py code served (permissive licence) · get_code("f3d59c152a2c3d9d") |
| grid_interp | Ran | autonomousvision/shape_as_points/src/dpsr.py code served (permissive licence) · get_code("591a3ae32bfd5a7e") |
| img | Ran | autonomousvision/shape_as_points/src/dpsr.py code served (permissive licence) · get_code("d77c3b9fe4c2a271") |
| point_rasterize | Ran | autonomousvision/shape_as_points/src/dpsr.py code served (permissive licence) · get_code("5938f95ef3a36917") |
| scatter_to_grid | Ran | autonomousvision/shape_as_points/src/dpsr.py code served (permissive licence) · get_code("1faee68fe4b27869") |
| spec_gaussian_filter | Ran | autonomousvision/shape_as_points/src/dpsr.py code served (permissive licence) · get_code("02fc59bb2d9cabd8") |
| DPSR | Not yet run | autonomousvision/shape_as_points/src/dpsr.py code served (permissive licence) · get_code("33eaba0ca11be07d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In recent years, neural implicit representations gained popularity in 3D reconstruction due to their expressiveness and flexibility. However, the implicit nature of neural implicit representations results in slow inference time and requires careful initialization. In this paper, we revisit the classic yet ubiquitous point cloud representation and introduce a differentiable point-to-mesh layer using a differentiable formulation of Poisson Surface Reconstruction (PSR) that allows for a GPUaccelerated fast solution of the indicator function given an oriented point cloud. The differentiable PSR layer allows us to efficiently and differentiably bridge the explicit 3D point representation with the 3D mesh via the implicit indicator field, enabling end-to-end optimization of surface reconstruction metrics such as Chamfer distance. This duality between points and meshes hence allows us to represent shapes as oriented point clouds, which are explicit, lightweight and expressive. Compared to neural implicit representations, our Shape-As-Points (SAP) model is more interpretable, lightweight, and accelerates inference time by one order of magnitude. Compared to other explicit representations such as points, patches, and meshes, SAP produces topology-agnostic, watertight manifold surfaces. We demonstrate the effectiveness of SAP on the task of surface reconstruction from unoriented point clouds and learning-based reconstruction.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.03452")
get_code_for_paper("2106.03452")
have("2106.03452")
Connect an agent — have() is free.