Long-Term Multi-Session 3D Reconstruction Under Substantial Appearance Change

• URL: http://arxiv.org/abs/2602.20584v1
• Date: Tue, 24 Feb 2026 06:12:51 GMT
• Title: Long-Term Multi-Session 3D Reconstruction Under Substantial Appearance Change
• Abstract summary: Long-term environmental monitoring requires the ability to reconstruct and align 3D models across repeated site visits separated by months or years.<n>Existing approaches rely on post-hoc alignment of independently reconstructed sessions.<n>We propose enforcing cross-session correspondences directly within a joint SfM reconstruction.
• Score: 52.46888249268445
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-term environmental monitoring requires the ability to reconstruct and align 3D models across repeated site visits separated by months or years. However, existing Structure-from-Motion (SfM) pipelines implicitly assume near-simultaneous image capture and limited appearance change, and therefore fail when applied to long-term monitoring scenarios such as coral reef surveys, where substantial visual and structural change is common. In this paper, we show that the primary limitation of current approaches lies in their reliance on post-hoc alignment of independently reconstructed sessions, which is insufficient under large temporal appearance change. We address this limitation by enforcing cross-session correspondences directly within a joint SfM reconstruction. Our approach combines complementary handcrafted and learned visual features to robustly establish correspondences across large temporal gaps, enabling the reconstruction of a single coherent 3D model from imagery captured years apart, where standard independent and joint SfM pipelines break down. We evaluate our method on long-term coral reef datasets exhibiting significant real-world change, and demonstrate consistent joint reconstruction across sessions in cases where existing methods fail to produce coherent reconstructions. To ensure scalability to large datasets, we further restrict expensive learned feature matching to a small set of likely cross-session image pairs identified via visual place recognition, which reduces computational cost and improves alignment robustness.

Related papers

• Global-Scale Self-Supervised Spatiotemporal Learning for NDVI Time-Series Reconstruction [9.201150739299447]
  We propose a Globalscale Self-supervised Spatiotemporal framework for NDVI Reconstruction.<n>The framework constructs supervisory signals by artificially relatively clean observations.<n>The proposed framework can accurately characterize vegetation dynamics and capture the keyphenological states.
  arXiv  Detail & Related papers  (2026-08-03T14:46:25Z)
• NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction [25.145305440192875]
  Pose-Free Feed-forward 3D Gaussian Splatting has recently emerged as a powerful paradigm for fast scene reconstruction.<n>However, its performance degrades significantly in long image sequences due to cumulative camera pose estimation drift.<n>We propose a synergistic pose-free framework that explicitly couples geometry and appearance via a Raymap-Guided Coupling Module.
  arXiv  Detail & Related papers  (2026-07-08T09:02:18Z)
• Global Structure-from-Motion Meets Feedforward Reconstruction [50.69771349993019]
  Structure-from-Motion is a central challenge in computer vision.<n>Recent advances in feedforward 3D reconstruction have made significant strides in overcoming persistent failure cases of classical SfM methods.<n>We propose a new Structure-from-Motion pipeline by combining the respective strengths of classical and feedforward methods.
  arXiv  Detail & Related papers  (2026-05-25T17:58:03Z)
• PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series Forecasting [6.1337977581640075]
  PESD-TSF is a physics-inspired structured decomposition framework for long-term time series forecasting.<n>It incorporates continuous-time priors to modulate signal amplitudes, preserving periodic structures across deep layers.<n>Experiments on benchmark datasets demonstrate that PESD-TSF consistently achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-05-15T03:11:52Z)
• Three-Stage Learning Unlocks Strong Performance in Simple Models for Long-Term Time Series Forecasting [6.603558172147427]
  STAIR aims to unlock the capacity of simple temporal mapping models without introducing complex architectural modules.<n>It first learns common temporal dynamics across variables through a shared temporal mapping, then adapts the shared model to each variable via channel-wise fine-tuning to capture variable-specific patterns, and finally complements the backbone with cross-variable information through residual learning.
  arXiv  Detail & Related papers  (2026-05-13T15:36:46Z)
• AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model [29.087865646035695]
  Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction.<n>We propose AnyRecon, a scalable framework for reconstruction from arbitrary and unordered sparse inputs.<n>Experiments demonstrate robust and scalable reconstruction across irregular inputs, large viewpoint gaps, and long trajectories.
  arXiv  Detail & Related papers  (2026-04-21T17:59:47Z)
• SSR: A Training-Free Approach for Streaming 3D Reconstruction [53.19807901585702]
  Self-expressive Sequence Regularization (SSR) is a plug-and-play operator that enforces Grassmannian sequence regularity during inference.<n>We show that SSR consistently reduces drift and improves reconstruction quality across multiple streaming 3D reconstruction tasks.
  arXiv  Detail & Related papers  (2026-03-16T02:55:14Z)
• CIPHER: Culvert Inspection through Pairwise Frame Selection and High-Efficiency Reconstruction [53.9319127526742]
  We present an efficient RGB-based 3D reconstruction pipeline for culvert-like structures in visually repetitive environments.<n>Our approach first selects informative frame pairs to maximize viewpoint diversity while ensuring valid correspondence matching.<n> Experiments demonstrate that our method effectively generates accurate 3D reconstructions and depth maps, enhancing culvert inspection efficiency with minimal human intervention.
  arXiv  Detail & Related papers  (2026-03-14T23:00:19Z)
• OnlineX: Unified Online 3D Reconstruction and Understanding with Active-to-Stable State Evolution [34.8105632078785]
  We introduce OnlineX, a feed-forward framework that reconstructs both 3D visual appearance and language fields in an online manner using only streaming images.<n>Our framework decouples the memory state into a dedicated active state and a persistent stable state, and then cohesively fuses the information from the former into the latter to achieve both fidelity and stability.
  arXiv  Detail & Related papers  (2026-03-02T17:52:02Z)
• A Decomposition-based State Space Model for Multivariate Time-Series Forecasting [0.0]
  We propose an end-to-end decomposition framework using three parallel deep state space model branches to capture trend, seasonal, and residual components.<n>Across standard benchmarks, DecompSSM outperformed strong baselines, indicating the effectiveness of combining component-wise deep state space models and global context refinement.
  arXiv  Detail & Related papers  (2026-02-05T07:17:08Z)
• InpaintHuman: Reconstructing Occluded Humans with Multi-Scale UV Mapping and Identity-Preserving Diffusion Inpainting [64.42884719282323]
  InpaintHuman is a novel method for generating high-fidelity, complete, and animatable avatars from occluded monocular videos.<n>Our approach employs direct pixel-level supervision to ensure identity fidelity.
  arXiv  Detail & Related papers  (2026-01-05T13:26:02Z)
• Morphing Through Time: Diffusion-Based Bridging of Temporal Gaps for Robust Alignment in Change Detection [51.56484100374058]
  We introduce a modular pipeline that improves spatial and temporal robustness without altering existing change detection networks.<n>A diffusion module synthesizes intermediate morphing frames that bridge large appearance gaps, enabling RoMa to estimate stepwise correspondences.<n>Experiments on LEVIR-CD, WHU-CD, and DSIFN-CD show consistent gains in both registration accuracy and downstream change detection.
  arXiv  Detail & Related papers  (2025-11-11T08:40:28Z)
• VEIGAR: View-consistent Explicit Inpainting and Geometry Alignment for 3D object Removal [2.8954284913103367]
  Novel View Synthesis (NVS) and 3D generation have significantly improved editing tasks.<n>To maintain cross-view consistency throughout the generative process, methods typically address this challenge using a dual-strategy framework.<n>We present VEIGAR, a computationally efficient framework that outperforms existing methods without relying on an initial reconstruction phase.
  arXiv  Detail & Related papers  (2025-06-13T11:31:44Z)
• StateSpaceDiffuser: Bringing Long Context to Diffusion World Models [52.92249035412797]
  We introduce StateSpaceDiffuser, where a diffusion model is enabled to perform long-context tasks by integrating features from a state-space model.<n>This design restores long-term memory while preserving the high-fidelity synthesis of diffusion models.
  arXiv  Detail & Related papers  (2025-05-28T11:27:54Z)
• TransformerLSR: Attentive Joint Model of Longitudinal Data, Survival, and Recurrent Events with Concurrent Latent Structure [35.54001561725239]
  We develop TransformerLSR, a flexible transformer-based deep modeling and inference framework to jointly model all three components simultaneously. We demonstrate the effectiveness and necessity of TransformerLSR through simulation studies and analyzing a real-world medical dataset on patients after kidney transplantation.
  arXiv  Detail & Related papers  (2024-04-04T20:51:37Z)
• REGAS: REspiratory-GAted Synthesis of Views for Multi-Phase CBCT Reconstruction from a single 3D CBCT Acquisition [75.64791080418162]
  REGAS proposes a self-supervised method to synthesize the undersampled tomographic views and mitigate aliasing artifacts in reconstructed images. To address the large memory cost of deep neural networks on high resolution 4D data, REGAS introduces a novel Ray Path Transformation (RPT) that allows for distributed, differentiable forward projections.
  arXiv  Detail & Related papers  (2022-08-17T03:42:19Z)
• Non-local Recurrent Regularization Networks for Multi-view Stereo [108.17325696835542]
  In deep multi-view stereo networks, cost regularization is crucial to achieve accurate depth estimation. We propose a novel non-local recurrent regularization network for multi-view stereo, named NR2-Net. Our method achieves state-of-the-art reconstruction results on both DTU and Tanks and Temples datasets.
  arXiv  Detail & Related papers  (2021-10-13T01:43:54Z)
• VIO-Aided Structure from Motion Under Challenging Environments [12.111638631118026]
  We present a robust and efficient Structure from Motion pipeline for accurate 3D reconstruction under challenging environments. Specifically, we propose a geometric verification method to filter out mismatches by considering the prior geometric configuration of candidate image pairs.
  arXiv  Detail & Related papers  (2021-01-24T06:35:52Z)
• Supporting Optimal Phase Space Reconstructions Using Neural Network Architecture for Time Series Modeling [68.8204255655161]
  We propose an artificial neural network with a mechanism to implicitly learn the phase spaces properties. Our approach is either as competitive as or better than most state-of-the-art strategies.
  arXiv  Detail & Related papers  (2020-06-19T21:04:47Z)

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.