LVSPM: Long Sequence View Synthesis and Pose Estimation Model

Abstract

We present LVSPM, a generalizable model that jointly estimates camera poses and synthesizes novel views from uncalibrated image collections. Trained with only RGB images and pose supervision, LVSPM avoids dense 3D ground truth and employs test-time training (TTT) layers to scale seamlessly to hundreds of input views. On RealEstate10k, Co3Dv2, and DL3DV, LVSPM surpasses VGGT in pose estimation across 16–256 views, with especially large margins at strict thresholds. For novel view synthesis under a practical protocol where more views cover larger scenes, LVSPM achieves state-of-the-art pose-free quality—surpassing even pose-dependent models in PSNR—and still maintains high quality as scene scale grows, while baselines collapse.

Method

LVSPM represents a scene as a sequence of image and camera tokens. Local view attention exchanges information among nearby views, while large-chunk test-time-training updates carry information through long sequences.

Citation

@inproceedings{chen2026lvspm,
  title     = {LVSPM: Long Sequence View Synthesis and Pose Estimation Model},
  author    = {Chen, Xi and Zhang, Yachi and Chen, Linghao and Liu, Minghua
               and Su, Hao and Xu, Zexiang and Zhang, Xiaoshuai},
  booktitle = {European Conference on Computer Vision},
  year      = {2026}
}