--- tags: - hand-reconstruction - egocentric-video - pytorch --- # InfiniHand Inference checkpoints for [InfiniHand](https://github.com/infinihand/InfiniHand). ## Checkpoints | Version | File | Training data | | --- | --- | --- | | [v1](v1) | `infinihand_v1.pt` | Our curated training corpus | | [egobench](egobench) | `infinihand_egobench.pt` | EgoBench | ## Usage Follow the [video and dataset inference guide](https://github.com/infinihand/InfiniHand#inference). Hand postprocessing is enabled by default; see [POST_PROCESS.md](https://github.com/infinihand/InfiniHand/blob/main/docs/POST_PROCESS.md). The shared model configuration uses `/path/to/...` placeholders. ## Training configuration The released training configurations use **Stage I: 300,000 steps** and **Stage II: 100,000 steps**. These describe the provided training recipe, not per-checkpoint iteration labels. See [DATA.md](https://github.com/infinihand/InfiniHand/blob/main/docs/DATA.md) and [training configurations](https://github.com/infinihand/InfiniHand/tree/main/configs/training). Third-party components retain their respective terms; see [NOTICE.md](https://github.com/infinihand/InfiniHand/blob/main/NOTICE.md). Exports were checked for tensor names, shapes, finite values and exact serialized-weight readback. Version names do not imply independently validated benchmark rankings.