SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images

• URL: http://arxiv.org/abs/2510.15072v1
• Date: Thu, 16 Oct 2025 18:37:10 GMT
• Title: SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images
• Authors: Jiaxin Guo, Tongfan Guan, Wenzhen Dong, Wenzhao Zheng, Wenting Wang, Yue Wang, Yeung Yam, Yun-Hui Liu,
• Abstract summary: SaLon3R is a novel framework for Structure-aware, Long-term 3DGS Reconstruction.<n>It is capable of reconstructing over 50 views in over 10 FPS, with 50% to 90% redundancy removal.<n>Our approach effectively resolves artifacts and prunes the redundant 3DGS in a single feed-forward pass.
• Score: 31.94503176488054
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have enabled generalizable, on-the-fly reconstruction of sequential input views. However, existing methods often predict per-pixel Gaussians and combine Gaussians from all views as the scene representation, leading to substantial redundancies and geometric inconsistencies in long-duration video sequences. To address this, we propose SaLon3R, a novel framework for Structure-aware, Long-term 3DGS Reconstruction. To our best knowledge, SaLon3R is the first online generalizable GS method capable of reconstructing over 50 views in over 10 FPS, with 50% to 90% redundancy removal. Our method introduces compact anchor primitives to eliminate redundancy through differentiable saliency-aware Gaussian quantization, coupled with a 3D Point Transformer that refines anchor attributes and saliency to resolve cross-frame geometric and photometric inconsistencies. Specifically, we first leverage a 3D reconstruction backbone to predict dense per-pixel Gaussians and a saliency map encoding regional geometric complexity. Redundant Gaussians are compressed into compact anchors by prioritizing high-complexity regions. The 3D Point Transformer then learns spatial structural priors in 3D space from training data to refine anchor attributes and saliency, enabling regionally adaptive Gaussian decoding for geometric fidelity. Without known camera parameters or test-time optimization, our approach effectively resolves artifacts and prunes the redundant 3DGS in a single feed-forward pass. Experiments on multiple datasets demonstrate our state-of-the-art performance on both novel view synthesis and depth estimation, demonstrating superior efficiency, robustness, and generalization ability for long-term generalizable 3D reconstruction. Project Page: https://wrld.github.io/SaLon3R/.

Related papers

• G3Splat: Geometrically Consistent Generalizable Gaussian Splatting [30.752029360892504]
  We introduce G3Splat, which enforces geometric priors to obtain geometrically consistent 3D scene representations.<n>Trained on RE10K, our approach achieves state-of-the-art performance in (i) geometrically consistent reconstruction, (ii) relative pose estimation, and (iii) novel-view synthesis.
  arXiv  Detail & Related papers  (2025-12-19T13:11:55Z)
• C3G: Learning Compact 3D Representations with 2K Gaussians [55.04010158339562]
  Recent approaches use per-pixel 3D Gaussian Splatting for reconstruction, followed by a 2D-to-3D feature lifting stage for scene understanding.<n>We propose C3G, a novel feed-forward framework that estimates compact 3D Gaussians only at essential spatial locations.
  arXiv  Detail & Related papers  (2025-12-03T17:59:05Z)
• Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstruction [30.518107360632488]
  Generalizable 3D Gaussian Splatting reconstruction showcases advanced Image-to-3D content creation.<n>method provides an efficient, scalable solution for real-world 3D content generation.
  arXiv  Detail & Related papers  (2025-07-20T11:33:13Z)
• FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction [50.534213038479926]
  FreeSplat++ is an alternative approach to large-scale indoor whole-scene reconstruction.<n>Our method with depth-regularized per-scene fine-tuning demonstrates substantial improvements in reconstruction accuracy and a notable reduction in training time.
  arXiv  Detail & Related papers  (2025-03-29T06:22:08Z)
• CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes [53.107474952492396]
  CityGaussianV2 is a novel approach for large-scale scene reconstruction.<n>We implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence.<n>Our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs.
  arXiv  Detail & Related papers  (2024-11-01T17:59:31Z)
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.<n>Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)
• Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting [33.01987451251659]
  3D Gaussian Splatting (3DGS) has emerged as a promising technique capable of real-time rendering with high-quality 3D reconstruction.<n>Despite its potential, 3DGS encounters challenges such as needle-like artifacts, suboptimal geometries, and inaccurate normals.<n>We introduce the effective rank as a regularization, which constrains the structure of the Gaussians.
  arXiv  Detail & Related papers  (2024-06-17T15:51:59Z)
• PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting [59.277480452459315]
  We propose a principled sensitivity pruning score that preserves visual fidelity and foreground details at significantly higher compression ratios.<n>We also propose a multi-round prune-refine pipeline that can be applied to any pretrained 3D-GS model without changing its training pipeline.
  arXiv  Detail & Related papers  (2024-06-14T17:53:55Z)
• latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction [48.86083272054711]
  latentSplat is a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture. We show that latentSplat outperforms previous works in reconstruction quality and generalization, while being fast and scalable to high-resolution data.
  arXiv  Detail & Related papers  (2024-03-24T20:48:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.