• [New] We upload the qualititative result on Google Drive Link
• We will release code. Coming Soon!!!!

• 🎯 Event-guided Deformable Feature Transfer Module

• 🔁 Dual-Memory Object Transformer

• 🧩 Memory Refinement Module

See Datasets & Installation

We trained with four A6000 GPUs, which took around 10 hours on LLE-VOS.

OMP_NUM_THREADS=4 torchrun --master_port 25357 --nproc_per_node=4 evolve/train.py exp_id=[some unique id] model=base data=base

• Change nproc_per_node to change the number of GPUs.
• Prepend CUDA_VISIBLE_DEVICES=... if you want to use specific GPUs.
• Change master_port if you encounter port collision.
• exp_id is a unique experiment identifier that does not affect how the training is done.
• Models and visualizations will be saved in ./output/.
• To load a pre-trained model, e.g., to continue main training from the final model from pre-training, specify weights=[path to the model].

• LLE-VOS Dataset

• LLE-DAVIS Dataset

@InProceedings{Baek_2025_ICCV,
    author    = {Baek, Jong-Hyeon and Oh, Jiwon and Koh, Yeong Jun},
    title     = {EVOLVE: Event-Guided Deformable Feature Transfer and Dual-Memory Refinement for Low-Light Video Object Segmentation},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2025},
    pages     = {11273-11282}
}