الملخص
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. The code is available at https://burningdust21.github.io/Projects/LVSPM .
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Chen, X., Zhang, Y., Chen, L., Liu, M., Su, H., Xu, Z., & Zhang, X. (2026). LVSPM: Long Sequence View Synthesis and Pose Estimation Model. https://omanscience.com/ar/articles/lvspm-long-sequence-view-synthesis-and-pose-estimation-model
MLA 9
Chen, Xi, et al. "LVSPM: Long Sequence View Synthesis and Pose Estimation Model." https://omanscience.com/ar/articles/lvspm-long-sequence-view-synthesis-and-pose-estimation-model.
شيكاغو (المؤلف–التاريخ)
Chen, Xi, Yachi Zhang, Linghao Chen, Minghua Liu, Hao Su, Zexiang Xu, and Xiaoshuai Zhang. 2026. "LVSPM: Long Sequence View Synthesis and Pose Estimation Model." https://omanscience.com/ar/articles/lvspm-long-sequence-view-synthesis-and-pose-estimation-model.
هارفارد
Chen, X., Zhang, Y., Chen, L., Liu, M., Su, H., Xu, Z. and Zhang, X. (2026) 'LVSPM: Long Sequence View Synthesis and Pose Estimation Model', Available at: https://omanscience.com/ar/articles/lvspm-long-sequence-view-synthesis-and-pose-estimation-model.
فانكوفر
Chen X, Zhang Y, Chen L, Liu M, Su H, Xu Z, et al. LVSPM: Long Sequence View Synthesis and Pose Estimation Model. https://omanscience.com/ar/articles/lvspm-long-sequence-view-synthesis-and-pose-estimation-model
IEEE
X. Chen, Y. Zhang, L. Chen, M. Liu, H. Su, Z. Xu, and X. Zhang, "LVSPM: Long Sequence View Synthesis and Pose Estimation Model," https://omanscience.com/ar/articles/lvspm-long-sequence-view-synthesis-and-pose-estimation-model.