BootsTAPIR (ONNX, 24-frame x 40-point window) for Perspectra

Redistribution of an existing open model, converted for the Perspectra Blender add-on. No retraining.

Original work: Google DeepMind, BootsTAPIR (https://github.com/google-deepmind/tapnet), checkpoint bootstapir_checkpoint_v2.pt
Licence: APACHE-2.0 — the same as the original weights. All credit to the original authors.
Paper: Doersch et al., BootsTAP: Bootstrapped Training for Tracking-Any-Point, ACCV 2024
Exported to ONNX with a fixed 24-frame window and 40 query points (256 x 256 input).

File	Size	SHA-256
`bootstapir_256.onnx`	221 MB	`51b6e02c87ceb3da…`

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support