mlsanityData to 7 Oct 2026

LVSPM: Long Sequence View Synthesis and Pose Estimation Model

arXiv 2610.10960 ↗First posted 7 Oct 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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 .

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 89 references that are in the map. First posted on arXiv 7 Oct 2026.

Builds on

23 of 89 references.

References · 23

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  2. 2020GLU Variants Improve Transformercited by 1,724
  3. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,283
  4. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  5. 2024Learning to (Learn at Test Time): RNNs with Expressive Hidden Statescited by 329
  6. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
  7. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
  8. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
  9. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  10. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  11. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 122
  12. 2025Test-Time Training Done Rightcited by 121
11 more
  1. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 111
  2. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  3. 2024MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereocited by 86
  4. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 74
  5. 2024InstantSplat: Sparse-view Gaussian Splatting in Secondscited by 67
  6. 2023LEAP: Liberate Sparse-view 3D Modeling from Camera Posescited by 65
  7. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  8. 2022SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstructioncited by 49
  9. 2024FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstructioncited by 40
  10. 2025No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Viewscited by 38
  11. 2025Test3R: Learning to Reconstruct 3D at Test Timecited by 19

Built on by

Not cited yet.