Downloads · 30 days
0
MemCam
newhorizon2005/MemCam
MemCam is a machine learning model from newhorizon2005. Use it for the machine learning 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.
IJCNN 2026 | Paper | Project Page | GitHub
Access
Public
Updated Mar 30, 2026
Repo size
3 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.ckpt3 GB · 99%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 26, 2026
- Updated
- Mar 30, 2026
- SHA
- 0d5557bb
Base models
Model card
From the Hugging Face model README
🎥 MemCam 🎥
Memory-Augmented Camera Control for Consistent Video Generation
IJCNN 2026 | Paper | Project Page | GitHub
Model Description
MemCam is a memory-augmented framework for scene-consistent interactive video generation, built on Wan2.1-T2V-1.3B. It treats previously generated frames as external memory and dynamically retrieves the most viewpoint-relevant frames via co-visibility estimation, enabling faithful scene reconstruction even after 360° camera rotations.
Files
| File | Description |
|---|---|
dit_step20000.ckpt | MemCam DiT checkpoint (trained 20k steps) |
Usage
git clone https://github.com/newhorizon2005/MemCam.git
cd MemCam
# Download this model
huggingface-cli download newhorizon2005/MemCam dit_step20000.ckpt --local-dir models/MemCam
# Run inference
python inference_memcam.py
Citation
@inproceedings{gao2026memcam,
title = {MemCam: Memory-Augmented Camera Control for Consistent Video Generation},
author = {Gao, Xinhang and Guan, Junlin and Luo, Shuhan and Li, Wenzhuo and Tan, Guanghuan and Wang, Jiacheng},
booktitle = {International Joint Conference on Neural Networks (IJCNN)},
year = {2026}
}
- License
- apache-2.0
- Created
- Mar 26, 2026
- Updated
- Mar 30, 2026