AccessPath
AccessPath is an anonymous-review release for accessibility-scene amodal
completion. It includes the full, finite GPU execution path from mask proposal
through quality-gated 2D completion and visual 3D completion. The package also
keeps two direct, mask-driven entry points:
- 2D completion: GPU inpainting that only changes the reviewed occluded
region and preserves source pixels elsewhere.
- Visual 3D completion: a wrapper around the separately released
Amodal3R backend that produces
Gaussian-splat and dense-mesh visual reconstructions from an RGB image and
an aligned three-value amodal mask.
The five supported accessibility categories are stairs, ramp, curb_cut,
tactile_paving, and walkway.
Relationship to prior work
AccessPath is inspired by and adapted from established research on promptable
segmentation, amodal completion, diffusion inpainting, monocular geometry, and
visual 3D reconstruction. It is not presented as a reimplementation or a copy
of any one prior system. The project-level contribution is the accessibility
adaptation: category-specific target/obstacle prompts, a visible-hidden-amodal
mask schema, constrained mask relations, mask-restricted 2D completion,
geometry/quality gates, a finite Slurm workflow, and review-oriented outputs.
When AccessPath actually calls an external model, that model remains an
independent backend with its own code, weights, and license. The precise
boundary between inspiration, optional comparison, and runtime use is listed
in
docs/DEPENDENCIES_AND_WEIGHTS.md.
What is included
This repository contains project-level pipeline, mask, 2D, depth/geometry,
visual-3D adapter, verification, rendering, review-bundle, Slurm, and prompt
configuration code. The complete process is documented in
docs/REPRODUCIBLE_PIPELINE.md, and the
stage-to-source mapping is in
docs/SOURCE_MANIFEST.md.
For a beginner-oriented installation guide, exact dependency status, official
model links, weight-download commands, and citation information, read
docs/DEPENDENCIES_AND_WEIGHTS.md before
running an experiment.
It deliberately contains no source images, masks, model checkpoints,
environments, experiment outputs, logs, author information, or
machine-specific paths.
The 100-image reviewer subset is not distributed yet. Its source-image and
derived-mask redistribution status requires source-specific license and
privacy clearance. A data card and a release manifest will be added only after
that review is complete.
Setup
Use Linux, Python 3.10+, a CUDA-capable GPU, and an environment compatible
with the chosen models. Create a fresh environment, install PyTorch for the
local CUDA version, then install the lightweight utilities:
1python -m pip install -r requirements/runtime.txt
2python -m pip install diffusers transformers accelerate safetensors
The visual-3D backend additionally needs the official Amodal3R environment
and its CUDA rasterizer dependencies. Follow the upstream installation guide;
do not copy the upstream source tree or checkpoints into this repository.
Obtain models separately
No weights are redistributed here. Download each dependency only after
accepting its own license and access conditions.
Project-trained checkpoints are intentionally withheld during anonymous review.
They should be released only after verifying the training-data permissions,
base-model terms, privacy risk, and the paper's release policy.
The optional VGGT path and the non-runtime related-work references
(pix2gestalt, Open-World AMODAL, and Amodal Completion in the Wild) are
identified explicitly in
docs/DEPENDENCIES_AND_WEIGHTS.md.
They are not silently downloaded or executed by the default pipeline.
Input masks
All masks must match the input RGB resolution. For 2D completion, provide the
visible-target, amodal-target, and obstacle masks. For visual 3D completion,
provide one aligned PNG with exactly these values:
1255 background
2188 visible target
30 hidden target
The intended relations are hidden = amodal AND NOT visible, visible and
obstacle are disjoint, and hidden is a subset of obstacle. Automatic masks are
proposals and should be reviewed before they drive a completion result.
Run 2D completion
1python accesspath.py 2d -- \
2 --image path/to/image.jpg \
3 --target-visible-mask path/to/target_visible.png \
4 --target-amodal-mask path/to/target_amodal.png \
5 --obstacle-mask path/to/obstacle.png \
6 --category stairs \
7 --model path/to/stable-diffusion-inpainting \
8 --output-dir outputs/example_2d \
9 --device cuda
The selected RGB result and its quality/provenance metadata are written under
the output directory. Run python accesspath.py 2d -- --help for all options.
Run the complete pipeline
The complete pipeline uses a bounded Slurm GPU job, so it queues for a GPU,
persists its result directory, and exits once the requested image is complete:
1python accesspath.py pipeline -- \
2 --image path/to/image.jpg \
3 --category stairs \
4 --output-dir outputs/stairs_demo
It runs mask proposals (or validates supplied reviewed masks), constrained
amodal-mask inference, 2D completion, depth/geometry diagnostics, visual 3D,
verification, and a compact review bundle. See
docs/REPRODUCIBLE_PIPELINE.md for environment
variables, stage-by-stage behavior, outputs, and optional stage switches.
Run visual 3D completion
Install the official Amodal3R runtime first, then run:
1python accesspath.py 3d -- \
2 --image path/to/image.jpg \
3 --mask path/to/amodal_3value.png \
4 --model Sm0kyWu/Amodal3R \
5 --output-dir outputs/example_3d
This is a learned visual reconstruction, not metric geometry, a navigation
safety label, or a guarantee of a watertight or scaled mesh. Run
python accesspath.py 3d -- --help for output and rendering options.
Attribution and release boundary
The 3D adapter calls Amodal3R and does not claim to reimplement that upstream
model. Consult
THIRD_PARTY_NOTICES.md and the model
cards for all dependency terms. Repository code is provided for anonymous
academic review; a final license and any project checkpoint release will be
announced with the archival paper release.
