Downloads · 30 days
0
anycam-mct
thekman17/anycam-mct
anycam-mct is a image-to-3d model from thekman17. Use it for the image-to-3d task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Final checkpoint of the master's thesis "Learning Camera Geometry from Unlabeled Real-World Dynamic Video" (TU Munich, 2026): AnyCam (CVPR 2025) extended with the Multi-Frame Calibration Transformer (MCT), a ~25M-para…
Access
Public
Updated Aug 17, 2026
Repo size
1.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.5 GB · 100%
At a glance
- Task
- Image-to-3D
- License
- apache-2.0
- Access
- Public
- Created
- Aug 8, 2026
- Updated
- Aug 17, 2026
- SHA
- 41fa3c42
Model card
From the Hugging Face model README
AnyCam-MCT — Multi-Frame Calibration Transformer
Final checkpoint of the master's thesis "Learning Camera Geometry from Unlabeled Real-World Dynamic Video" (TU Munich, 2026): AnyCam (CVPR 2025) extended with the Multi-Frame Calibration Transformer (MCT), a ~25M-parameter cross-frame attention module that aggregates AnyCalib features over multiple frames for video calibration, coupled to AnyCam's pose head via a focal embedding. Trained fully self-supervised on ~82k frames of in-the-wild video; this checkpoint includes the August 2026 correction pass (evaluation bugs fixed, calibration branch retrained with proper input normalization, checkpoint selected by validation loss).
Code, benchmarks, and reproduction instructions: https://github.com/kalman17/mcvo
Headline results (honest protocol, raw rows in the GitHub repo; tables updated 17 August 2026 — see the repo CHANGELOG)
| Measurement | This model | Competitors measured |
|---|---|---|
| Focal error, native wide KITTI frames (own preprocessing each) | 15.7 % | 11.6 % VGGT-1B · 14.2 % AnyCalib · 20.4 % Pi3 · 38.0 % DA3 |
| Focal error, KITTI windows | 20.4 % | 18.4 % AnyCalib · 66.9 % AnyCam |
| Focal error, Sintel / TUM-RGBD windows | 20.7 % / 12.9 % | 20.1 % / 11.2 % AnyCalib |
| Rotation error, Sintel (median) | 0.40° | 0.50° (AnyCam) |
Known limitations (stated in the repo README): calibration is on par with the single-image specialist, not beyond it, and multi-frame aggregation does not beat per-frame averaging for this checkpoint; translation direction on TUM-RGBD is worse than AnyCam; large supervised models (Depth Anything 3) lead absolute pose accuracy; full-trajectory drift vs long-context AnyCam inference.
Cost (NVIDIA A40, 4-frame window, end-to-end)
| Params | Peak GPU mem | Latency | |
|---|---|---|---|
| MCT calibration branch alone | 346 M (25 M trained) | 1.4 GiB | 161 ms |
| Full thesis pipeline (MCT + AnyCam pose, incl. depth/flow nets) | 460 M | 5.0 GiB | 820 ms |
Follow-up image-only VO model (thekman17/mcvo) | 154 M | 0.69 GiB | 75 ms |
Same GPU / windows / protocol as the comparison against VGGT, π³ and Depth Anything 3 in the GitHub README (honest_benchmarks/latency_summary.json).
Files
mct_final.pt— merged inference checkpoint (pose predictor + MCT calibration branch; load withexperiments/benchmark_phase_c_checkpoints.py:create_inference_modelload_phase_c_checkpointfrom the GitHub repo,input_normalization=True).
License / attribution
Apache-2.0. Contains weights derived from AnyCam (MIT, Wimbauer et al., CVPR 2025) and AnyCalib (Apache-2.0, Tirado-Garín et al., ICCV 2025); DINOv2 backbones (Apache-2.0, Meta). Please cite those works alongside the thesis.
- Task
- Image-to-3D
- License
- apache-2.0
- Created
- Aug 8, 2026
- Updated
- Aug 17, 2026