Views
No views yet
requirements.txt.StableMotion_SIR and StableMotion_RSC respectively.cd StableMotion_SIR && sh sample.sh. You may want to change this file to modify the inference configurations.sh metrics.sh to evaluate the results.StableMotion_SIR/MDM_Flow.cd StableMotion_SIR && sh train.sh. You may want to change this file to modify the training configurations. The default configuration requires approximately 80 GB of VRAM per card.cd StableMotion_RSC && sh sample.sh. You may want to change this file to modify the inference configurations.sh metrics.sh to evaluate the results.cd StableMotion_RSC && sh train.sh. You may want to change this file to modify the training configurations. The default configuration requires approximately 40 GB of VRAM per card.gpt_eval subfolder with the script used in the paper to score results with a vision LLM (GPT) on a fixed rubric. StableMotion_SIR/gpt_eval/score_rectangle.py scores Stitched Image Rectangling (SIR) (input, output) pairs, and StableMotion_RSC/gpt_eval/score_rolling_shutter.py scores Rolling Shutter Correction (RSC) [input | Yang | Ours] triptychs. Both call an OpenAI-Responses-compatible API and emit per-pair scores plus an aggregate summary.json (mean/std/95% CI). To run, copy provider.example.json to provider.json in the relevant folder, add your endpoint/key, then e.g. cd StableMotion_SIR/gpt_eval && python score_rectangle.py <input_dir> <result_dir>. See each folder's README.md for the full rubric, flags, and outputs.1@article{wang2025stablemotion,
2 title={StableMotion: One-Step Motion Estimation with Diffusion Prior},
3 author={Wang, Ziyi and Li, Haipeng and Sui, Lin and Zhou, Tianhao and Jiang, Hai and Nie, Lang and Liu, Shuaicheng},
4 journal={arXiv preprint arXiv:2505.06668},
5 year={2025}
6}