hongchi/Fire3D
Fire3D Processed Inference Data Paper | Code | Models Fire3D is a unified feed-forward framework that transforms a single RGB image or casual RGB video into simulation-ready 3D scene assets. It predicts a compositional scene representation with object-level 6-DoF pose, bounding box, mesh geometry, and texture, without test-time optimization. This release provides the inference code, model checkpoints, processed example inputs, and frozen protocols needed to reproduce Fire3D… See the full description on the dataset page: https://huggingface.co/datasets/hongchi/Fire3D.
| Author / organization | hongchi |
|---|---|
| License (as declared) | other |
| Downloads | 435 (as reported by Hugging Face) |
| Likes | 1 |
| Created | 7 September 2026 |
| Last updated at source | 9 September 2026 |
Popularity, last 3 days
435 now (-356 since 2026-10-16). Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
Recent changes
- 18 Oct 2026 Description: none → Fire3D Processed Inference Data Paper | Code | Models Fire3D is a unified feed-forward framework that transforms a single RGB image or casual RGB video into simulation-ready 3D scene assets. It predicts a compositional scene representation
- 18 Oct 2026 Topics added task_categories:image-to-3d, ithor, imaginarium, scannetpp removed fire3d, flow-matching, textured-mesh, image-to-3d
- 18 Oct 2026 Task: image-to-3d → none
- 18 Oct 2026 Topics added fire3d, flow-matching, textured-mesh, image-to-3d removed task_categories:image-to-3d, ithor, imaginarium, scannetpp
- 18 Oct 2026 Task: none → image-to-3d
- 17 Oct 2026 Description: none → Fire3D Processed Inference Data Paper | Code | Models Fire3D is a unified feed-forward framework that transforms a single RGB image or casual RGB video into simulation-ready 3D scene assets. It predicts a compositional scene representation
- 17 Oct 2026 Topics added task_categories:image-to-3d, ithor, imaginarium, scannetpp removed fire3d, flow-matching, textured-mesh, image-to-3d
- 17 Oct 2026 Task: image-to-3d → none
- 17 Oct 2026 Topics added fire3d, flow-matching, textured-mesh, image-to-3d removed task_categories:image-to-3d, ithor, imaginarium, scannetpp
- 17 Oct 2026 Task: none → image-to-3d
- 17 Oct 2026 Description: none → Fire3D Processed Inference Data Paper | Code | Models Fire3D is a unified feed-forward framework that transforms a single RGB image or casual RGB video into simulation-ready 3D scene assets. It predicts a compositional scene representation
- 17 Oct 2026 Topics added task_categories:image-to-3d, ithor, imaginarium, scannetpp removed fire3d, flow-matching, textured-mesh, image-to-3d
Changes detected by Silytics between refreshes of the source.
Related papers
Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.