Guomh0707/V-RAE-Models

V-RAE: Rethinking Video Latent Spaces for Generation

Minghui Guo¹    Shengqiong Wu²    Hao Fei²

¹National University of Singapore    ²University of Oxford

V-RAE is a video representation autoencoder that builds compact generative latents on top of frozen vision foundation model representations. It uses a lightweight temporal pooling module to remove temporal redundancy while preserving semantic structure, together with a video decoder for reconstructing continuous motion.

Released Models

This repository provides V-RAE checkpoints based on four frozen visual encoders:

Checkpoint	Encoder
vrae/vrae_dinov3.pt	DINOv3 ViT-L/16
vrae/vrae_siglip2.pt	SigLIP2 ViT-L/16
vrae/vrae_vjepa2.1.pt	V-JEPA2.1 ViT-L/16
vrae/vrae_eupe.pt	EUPE ViT-B/16

Class-conditional VideoDiT checkpoints and their matching latent statistics are also provided for UCF101 and Kinetics-600:

• UCF101: V-JEPA2.1 and EUPE variants
• Kinetics-600: V-JEPA2.1 variant

Quick Start

Install the official implementation:

git clone https://github.com/V-RAE/V-RAE.git
cd V-RAE

conda create -n vrae python=3.10 -y
conda activate vrae
conda install -c conda-forge ffmpeg -y

pip install uv
uv pip install -e .

Download the released checkpoints:

hf download Guomh0707/V-RAE-Models --local-dir ckpts

Download the matching frozen encoder by following the encoder instructions.

Place three input videos at assets/sample1.mp4, assets/sample2.mp4, and assets/sample3.mp4, then run one of:

python sampling.py dino
python sampling.py siglip
python sampling.py vjepa
python sampling.py eupe

Reconstruction results are saved under outputs/<variant>/.

Results

Evaluation	Result
Kinetics-600 reconstruction	2.13 rFVD
UCF101 class-conditional generation	117.86 gFVD
Kinetics-600 class-conditional generation	19.16 gFVD

Notes

• Each V-RAE checkpoint requires its corresponding frozen encoder weights.
• These are custom PyTorch checkpoints and require the official V-RAE codebase.
• This repository is intended primarily for research use.

Citation

@article{guo2026vrae,
  title   = {V-RAE: Rethinking Video Latent Spaces for Generation},
  author  = {Guo, Minghui and Wu, Shengqiong and Fei, Hao},
  journal = {arXiv preprint arXiv:2608.13556},
  year    = {2026},
}