TALON: Token-Aligned Lightweight Adapters for 6-DoF Spacecraft Pose Estimation

• URL: http://arxiv.org/abs/2605.31217v1
• Date: Fri, 29 May 2026 12:21:52 GMT
• Title: TALON: Token-Aligned Lightweight Adapters for 6-DoF Spacecraft Pose Estimation
• Abstract summary: Monoattention 6-F spacecraft pose estimation methods process individual frames, discarding the temporal information present in an image sequence acquired during manoeuvres.<n>We propose TALON (Token-conditioned adapters): 3D adapters injected before self-tuning layers of a frozen ViT vision transformer.<n>Pre-Aligned allows the frozen attention to reason over temporally enriched tokens, achieving stronger performance with a single adapter per block than post-attention alternatives.<n>On SPADES dataset, TA reduces the pose error by 50% over the prior state-of-the-art, and on Swiss dataset it surpasses the prior best by 21.8% in ADD-0.1d
• Score: 14.854437007037683
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Monocular 6-DoF spacecraft pose estimation methods predominantly process individual frames, discarding the temporal information present in an image sequence acquired during spacecraft manoeuvres. Few temporal approaches require full backbone fine-tuning or auxiliary optical flow networks, risking catastrophic forgetting or increasing computational cost, respectively. We propose TALON (Token-Aligned Lightweight adapters for Orbital Navigation): spatiotemporal 3D adapters injected before the self-attention layers of a frozen ViT vision transformer, combined with a patch-token alignment loss that geometrically grounds the adapted features to keypoint structure through a prototype-conditioned KL-divergence objective. Pre-attention placement allows the frozen attention to reason over temporally enriched tokens, achieving stronger performance with a single adapter per block than post-attention alternatives. The alignment loss shapes the intermediate representations so that each keypoint induces a spatially precise activation in the token field, while the framework adds less than 5% parameters to the frozen backbone. On SPADES dataset, TALON reduces the pose error by 50% over the prior state-of-the-art, and on SwissCube dataset it surpasses the prior best by 21.8% in ADD-0.1d accuracy. Zero-shot cross-domain evaluation from sim-to-real on SPARK real data reduces pose error by 4.7x, and ablations characterise the role of adapter depth across in-domain and cross-domain settings.

Related papers

• Cut-ViT: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency [71.81785123423516]
  We propose a task-specific pruning pipeline, named Cut-ViT, for pruning visual foundation models.<n> Basis-agnostic and residual constraints are adopted to align the gram subspaces between the native and pruned DINOv3 models.<n>Experiments show that Cut-ViT requires approximately one minute on a single A100 GPU to obtainworks at various sparsity levels.
  arXiv  Detail & Related papers  (2026-08-28T11:25:36Z)
• TinyDETR-Pose: Towards End-to-End Real-Time Single-Stage 6DoF Object Pose Estimation with Lightweight Transformers [11.190709946582166]
  We present TinyDETR-Pose, a lightweight, end-to-end, single-stage pose estimation approach.<n>TinyDETR-Pose regresses their 6D pose in a single forward pass.<n>On YCB-V, TinyDETR-Pose achieves a comparable ADD-S AUC 85.9, while requiring up to 7 fewer parameters than other DETR-based single-stage pose estimation approaches.
  arXiv  Detail & Related papers  (2026-08-15T16:02:51Z)
• OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos [76.81099730054356]
  We present OrthoTrack, a training-free system that estimates continuous 6-DoF trajectories using only publicly available orthophotos and surface models as a map prior.<n>On MovingDrone and real-world benchmarks, OrthoTrack runs in real time on a single GPU. It outperforms all baselines by a large margin, even those receiving oracle scale and alignment.
  arXiv  Detail & Related papers  (2026-06-24T00:05:01Z)
• Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model [0.0]
  Prithvi-EO has shown strong transferability across computer vision tasks.<n>It produces features at a single spatial scale that are ill-suited for the multi-scale features required by object detection heads.<n>We show that lightweight spatial prior fusion and selective backbone unfreezing enable Prithvi-EO to capture local fallow patterns more effectively.
  arXiv  Detail & Related papers  (2026-06-10T15:31:37Z)
• Continuous Neural Reparameterization as a Deep Geometric Prior for Robust Fixed-Chart UV Repair [0.0]
  We recast fixed-chart UV unwrapping as continuous neural reparameterization.<n>We combine Laplace--Beltrami spectral inputs, Tutte residual warm-up, a $C2$ determinant extension, and validity-checked retry/fallback routing.<n>On compact pre-cut charts and a 47-chart stratified Thingi10K/xatlas-cut benchmark, the neural solver produces zero flips on all compact charts and 42/47 valid zero-flip stratified solves.
  arXiv  Detail & Related papers  (2026-06-08T18:26:03Z)
• Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders [123.58723804218151]
  Vision foundation models are bottlenecked by the quadratic cost of self-attention.<n>We present C-GSPN based on 2D spatial propagation propagation.
  arXiv  Detail & Related papers  (2026-05-30T14:29:43Z)
• Point-MF: One-step Point Cloud Generation from a Single Image via Mean Flows [4.719615308536812]
  Single-image point cloud reconstruction must infer complete 3D geometry, including occluded parts, from a single RGB image.<n>We propose Point-MF, a Mean-Flow-based framework for low-NFE single-image point cloud reconstruction.
  arXiv  Detail & Related papers  (2026-04-27T15:10:47Z)
• FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation [43.11840324722107]
  Esting the 6-degrees-of-freedom pose of a spacecraft from a single image is critical for autonomous operations like in-orbit servicing and space debris removal.<n>We propose FastPose-ViT, a Vision Transformer (ViT)-based architecture that directly regresses the 6DoF pose.<n>Our approach processes cropped images from object bounding boxes and introduces a novel mathematical formalism to map these localized predictions back to the full-image scale.
  arXiv  Detail & Related papers  (2025-12-10T16:11:00Z)
• IPA: An Information-Preserving Input Projection Framework for Efficient Foundation Model Adaptation [56.72132739364876]
  We propose IPA, a feature-aware projection framework that explicitly preserves information in the reduced hidden space.<n> IPA consistently improves over LoRA and DoRA, achieving on average 1.5 points higher accuracy on commonsense reasoning.
  arXiv  Detail & Related papers  (2025-09-04T17:10:01Z)
• Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis [51.37795317716487]
  We propose the Adaptive Point-Prompt Tuning (APPT) method, which fine-tunes pre-trained models with a modest number of parameters.<n>We convert raw point clouds into point embeddings by aggregating local geometry to capture spatial features followed by linear layers.<n>To calibrate self-attention across source domains of any modality to 3D, we introduce a prompt generator that shares weights with the point embedding module.
  arXiv  Detail & Related papers  (2025-08-30T06:02:21Z)
• High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery [6.902247657565531]
  We introduce HEDS-DETR, a holistically enhanced real-time Detection Transformer tailored for aerial scenes.<n>First, we propose a novel High-Frequency Enhanced Semantics Network (HFESNet) backbone, which yields highly discriminative features.<n>Second, our Efficient Small Object Pyramid (ESOP) counteracts information loss by efficiently fusing high-resolution features.<n>Third, we enhance decoder stability and localization precision with two synergistic components.
  arXiv  Detail & Related papers  (2025-07-01T14:56:56Z)
• Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning [49.91297276176978]
  We propose a novel intrinsic textbfPointGST (textbfGraph textbfSpectral textbfTuning) method for point cloud.<n>Point GST freezes the pre-trained model and introduces a lightweight, trainable Point Cloud Spectral Adapter (PCSA) for fine-tuning parameters in the spectral domain.<n>Experiments on challenging point cloud datasets across various tasks demonstrate that Point GST not only outperforms its fully fine-tuning counterpart but also significantly reduces trainable parameters.
  arXiv  Detail & Related papers  (2024-10-10T17:00:04Z)
• CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs [65.80187860906115]
  We propose a novel approach to improve NeRF's performance with sparse inputs. We first adopt a voxel-based ray sampling strategy to ensure that the sampled rays intersect with a certain voxel in 3D space. We then randomly sample additional points within the voxel and apply a Transformer to infer the properties of other points on each ray, which are then incorporated into the volume rendering.
  arXiv  Detail & Related papers  (2024-03-25T15:56:17Z)
• Coordinate Transformer: Achieving Single-stage Multi-person Mesh Recovery from Videos [91.44553585470688]
  Multi-person 3D mesh recovery from videos is a critical first step towards automatic perception of group behavior in virtual reality, physical therapy and beyond. We propose the Coordinate transFormer (CoordFormer) that directly models multi-person spatial-temporal relations and simultaneously performs multi-mesh recovery in an end-to-end manner. Experiments on the 3DPW dataset demonstrate that CoordFormer significantly improves the state-of-the-art, outperforming the previously best results by 4.2%, 8.8% and 4.7% according to the MPJPE, PAMPJPE, and PVE metrics, respectively.
  arXiv  Detail & Related papers  (2023-08-20T18:23:07Z)

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.