4RC

Project Page | Arxiv | GitHub

This repo contains the pretrained weights for 4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere.

4RC (pronounced "ARC") enables unified and complete 4D reconstruction via conditional querying from monocular videos in a single feed-forward pass.

Usage

To load the model:

import torch
from arc.models.arc.arc import Arc

device = "cuda" if torch.cuda.is_available() else "cpu"
model = Arc.from_pretrained("Luo-Yihang/4RC_geofinetune").to(device)
model.eval()

Please refer to our repo for more details on loading and inference.

Citation

@article{luo20264rc,
    title={4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere},
    author={Yihang Luo and Shangchen Zhou and Yushi Lan and Xingang Pan and Chen Change Loy},
    journal={arXiv preprint arXiv:2602.10094},
    year={2026},
}