We lifted 10 functions out of this paper's own repositories and ran 9 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 |
|---|---|---|
| computational-imaging/ACORN | canonical | 9 of 10 |
| Function | Status | Where it lives |
|---|---|---|
| define_grid_3d | Ran | computational-imaging/ACORN/metrics.py code served (permissive licence) · get_code("e465503975d6f0dc") |
| dict2cpu | Ran | computational-imaging/ACORN/utils.py code served (permissive licence) · get_code("fb7bf7a07ca1e5c2") |
| dict2cuda | Ran | computational-imaging/ACORN/utils.py code served (permissive licence) · get_code("0a69fd37a19d8c73") |
| get_mgrid | Ran | computational-imaging/ACORN/dataio.py code served (permissive licence) · get_code("cd78367e88d9ebaf") |
| grads2img | Ran | computational-imaging/ACORN/dataio.py code served (permissive licence) · get_code("688fa41cff60b7e8") |
| image_mse | Ran | computational-imaging/ACORN/loss_functions.py code served (permissive licence) · get_code("2916c18c7b78b757") |
| lin2img | Ran | computational-imaging/ACORN/dataio.py code served (permissive licence) · get_code("9d902c538061fea5") |
| load_from_checkpoint | Ran | computational-imaging/ACORN/experiment_scripts/train_occupancy.py code served (permissive licence) · get_code("14a9c52408327bfd") |
| occupancy_bce | Ran | computational-imaging/ACORN/loss_functions.py code served (permissive licence) · get_code("e845024625a8e2e2") |
| check_mesh_contains | Not yet run | computational-imaging/ACORN/inside_mesh/inside_mesh.py code served (permissive licence) · get_code("01c313d022801b92") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Neural representations have emerged as a new paradigm for applications in rendering, imaging, geometric modeling, and simulation. Compared to traditional representations such as meshes, point clouds, or volumes they can be flexibly incorporated into differentiable learning-based pipelines. While recent improvements to neural representations now make it possible to represent signals with fine details at moderate resolutions (e.g., for images and 3D shapes), adequately representing large-scale or complex scenes has proven a challenge. Current neural representations fail to accurately represent images at resolutions greater than a megapixel or 3D scenes with more than a few hundred thousand polygons. Here, we introduce a new hybrid implicit-explicit network architecture and training strategy that adaptively allocates resources during training and inference based on the local complexity of a signal of interest. Our approach uses a multiscale block-coordinate decomposition, similar to a quadtree or octree, that is optimized during training. The network architecture operates in two stages: using the bulk of the network parameters, a coordinate encoder generates a feature grid in a single forward pass. Then, hundreds or thousands of samples within each block can be efficiently evaluated using a lightweight feature decoder. With this hybrid implicit-explicit network architecture, we demonstrate the first experiments that fit gigapixel images to nearly 40 dB peak signal-to-noise ratio. Notably this represents an increase in scale of over 1000x compared to the resolution of previously demonstrated image-fitting experiments. Moreover, our approach is able to represent 3D shapes significantly faster and better than previous techniques; it reduces training times from days to hours or minutes and memory requirements by over an order of magnitude.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2105.02788")
get_code_for_paper("2105.02788")
have("2105.02788")
Connect an agent — have() is free.