---
license: mit
tags:
  - 3d-reconstruction
  - affordance-grounding
  - flow-matching
  - rgbd
arxiv: 2601.09211
---

# Affostruction

**Affostruction: 3D Affordance Grounding with Generative Reconstruction** — CVPR 2026, Denver.

[Chunghyun Park](https://chrockey.github.io/)<sup>1</sup>,
[Seunghyeon Lee](https://llishyun.github.io/)<sup>1</sup>,
[Minsu Cho](http://cvlab.postech.ac.kr/~mcho/)<sup>1,2</sup>

<sup>1</sup>POSTECH &nbsp;&nbsp; <sup>2</sup>RLWRLD

- Paper: https://arxiv.org/abs/2601.09211
- Project page: https://chrockey.github.io/Affostruction/
- Code: https://github.com/chrockey/Affostruction

Pretrained checkpoints for the public release.

## Reconstruction

```python
from affostruction import ReconstructionPipeline

pipeline = ReconstructionPipeline.from_pretrained("chrockey/Affostruction").cuda()
outputs = pipeline.run(input_dict)
mesh = outputs["mesh"][0]
gaussian = outputs["gaussian"][0]
```

Input format — see `examples/reconstruction.py` in the repo.

## Affordance grounding

```python
from affostruction.pipeline import AffordancePipeline

pipeline = AffordancePipeline.from_pretrained("chrockey/Affostruction")
# NOTE: pipeline.run() is not yet wired in the release package.
# Downloads + parses the checkpoint; full inference requires ElasticSLatFlowModel
# to be registered in affostruction/models/.
```