GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

Tian-Xing Xu, xiangjun gao, Wenbo Hu, Xiaoyu Li, Song-Hai Zhang, Ying Shan

GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors: 30 upvotes on Hugging Face Daily Papers, #7 of 29 papers on 2025-04-02. Day-by-day upvote history.

Despite remarkable advancements in video depth estimation, existing methods exhibit inherent limitations in achieving geometric fidelity through the affine-invariant predictions, limiting their applicability in reconstruction and other metrically grounded downstream tasks. We propose GeometryCrafter, a novel framework that recovers high-fidelity point map sequences with temporal coherence from open-world videos, enabling accurate 3D/4D reconstruction, camera parameter estimation, and other depth-based applications. At the core of our approach lies a point map Variational Autoencoder (VAE) that learns a latent space agnostic to video latent distributions for effective point map encoding and decoding. Leveraging the VAE, we train a video diffusion model to model the distribution of point map sequences conditioned on the input videos. Extensive evaluations on diverse datasets demonstrate that GeometryCrafter achieves state-of-the-art 3D accuracy, temporal consistency, and generalization capability.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.