We lifted 7 functions out of this paper's own repositories and ran 2 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 |
|---|---|---|
| eigenvivek/diffpose | canonical | 2 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| gradient_matching | Ran | eigenvivek/diffpose/diffpose/jacobians.py code served (permissive licence) · get_code("ad0fe3fcf11547a7") |
| preprocess | Ran | eigenvivek/diffpose/diffpose/registration.py code served (permissive licence) · get_code("2bc0a545d2f0f856") |
| fiducials_3d_to_projected_fiducials_3d | Not yet run | eigenvivek/diffpose/diffpose/visualization.py code served (permissive licence) · get_code("716450e4709a6ac8") |
| img_to_patches | Not yet run | eigenvivek/diffpose/diffpose/registration.py code served (permissive licence) · get_code("72daf76d1d3732de") |
| overlay_edges | Not yet run | eigenvivek/diffpose/diffpose/visualization.py code served (permissive licence) · get_code("cbbe2f0022037986") |
| plot_img_jacobian | Not yet run | eigenvivek/diffpose/diffpose/jacobians.py code served (permissive licence) · get_code("157e7d9f4d09aa4f") |
| pred_to_patches | Not yet run | eigenvivek/diffpose/diffpose/registration.py code served (permissive licence) · get_code("d07e4c250f9ec51b") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Surgical decisions are informed by aligning rapid portable 2D intraoperative images (e.g., X-rays) to a high-fidelity 3D preoperative reference scan (e.g., CT). 2D/3D image registration often fails in practice: conventional optimization methods are prohibitively slow and susceptible to local minima, while neural networks trained on small datasets fail on new patients or require impractical landmark supervision. We present DiffPose, a self-supervised approach that leverages patient-specific simulation and differentiable physics-based rendering to achieve accurate 2D/3D registration without relying on manually labeled data. Preoperatively, a CNN is trained to regress the pose of a randomly oriented synthetic X-ray rendered from the preoperative CT. The CNN then initializes rapid intraoperative test-time optimization that uses the differentiable X-ray renderer to refine the solution. Our work further proposes several geometrically principled methods for sampling camera poses from $\mathbf{SE}(3)$, for sparse differentiable rendering, and for driving registration in the tangent space $\mathfrak{se}(3)$ with geodesic and multiscale locality-sensitive losses. DiffPose achieves sub-millimeter accuracy across surgical datasets at intraoperative speeds, improving upon existing unsupervised methods by an order of magnitude and even outperforming supervised baselines. Our code is available at https://github.com/eigenvivek/DiffPose.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2312.06358")
get_code_for_paper("2312.06358")
have("2312.06358")
Connect an agent — have() is free.