TinyDETR-Pose: Towards End-to-End Real-Time Single-Stage 6DoF Object Pose Estimation with Lightweight Transformers

• URL: http://arxiv.org/abs/2608.15297v1
• Date: Sat, 15 Aug 2026 16:02:51 GMT
• Title: TinyDETR-Pose: Towards End-to-End Real-Time Single-Stage 6DoF Object Pose Estimation with Lightweight Transformers
• Abstract summary: 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.
• Score: 11.190709946582166
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-time 6DoF object pose estimation on resource-constrained hardware remains challenging, as accurate correspondence-based and refinement pipelines typically rely on non-differentiable PnP/RANSAC stages or costly iterative refinement, while recent foundation-model-based approaches incur inference costs that are prohibitive for edge deployment. We present TinyDETR-Pose, a lightweight, end-to-end, single-stage framework that jointly detects objects and regresses their full 6D pose in a single forward pass. Built on the efficient LW-DETR architecture, TinyDETR-Pose formulates detection and pose estimation as a set-prediction problem and attaches dedicated MLP heads for rotation, monocular depth, and projected object center regression to each decoder query, eliminating the need for PnP, NMS (non-maximum suppression), or iterative pose refinement. Object symmetries are handled through a ADD-S loss applied uniformly to all objects, without the need for object-specific loss schedules or separate geodesic/ADD supervision. In addition, predictions are assigned to ground truth using a symmetry-safe Hungarian matcher based on class and 2D spatial cues, yielding stable assignment under symmetry and depth ambiguity. On YCB-V, TinyDETR-Pose achieves a comparable ADD-S AUC of 85.9, while requiring up to 72.7% fewer parameters than other DETR-based single-stage pose-estimation approaches. Due to its compact design, TinyDETR-Pose runs in real time and achieves an inference latency of only ~4.5 ms per frame on an NVIDIA Jetson Nano using TensorRT, demonstrating that accurate end-to-end transformer-based 6D pose estimation can be made practical for edge deployment.

Related papers

• Back to the Feature: Zero-Shot 6DoF Pose Estimation via Dense Local Features [0.0]
  We present B2ose, a training-free zero-shot method for 6DoF pose estimation of unseen objects from RGB images.<n>B2ose extracts dense patch-level features that generalize across the synthetic-to-real domain gap without task-specific fine-tuning.<n>On the seven core datasets of the BOP Benchmark, B2ose achieves 40.7 mean AR without refinement and 56.4 refinement.
  arXiv  Detail & Related papers  (2026-09-06T16:57:27Z)
• RRTrack: Robust and Recoverable Object 6D Pose Tracking for Dynamic Scenes [55.15267980622371]
  RRTrack is an efficient, recoverable object 6D pose tracker.<n>It enables robust tracking through fast motion and target disappearance--reappearance.<n>Experiments show RRTrack improves equal-subset mean ADD-S AR by 66.3% and ADD-S AUC by 65.7% over FoundationPose.
  arXiv  Detail & Related papers  (2026-07-26T14:05:46Z)
• Pose Anything Anywhere:Model-free Object Poses from Arbitrary References [64.58017857473774]
  We present PANY, a model-free framework that seamlessly supports both RGB and RGB-D inputs.<n>It operates on one or sparse pose-free reference views, and generalizes effectively to novel objects.<n>It achieves state-of-the-art performance across multiple benchmarks, substantially outperforming existing model-free methods.
  arXiv  Detail & Related papers  (2026-06-22T17:23:57Z)
• MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation [21.294005937994882]
  MAPRPose is a two-stage framework that leverages mask-aware correspondences for pose proposal and amodal-driven Region-of-Interest (ROI) prediction for robust refinement.<n> evaluated on the BOP benchmark, MAPRPose achieves a state-of-the-art Average Recall (AR) of 76.5%, outperforming FoundationPose by 3.1% AR while delivering a 43x speedup in multi-object inference.
  arXiv  Detail & Related papers  (2026-04-22T15:00:46Z)
• Yolo-Key-6D: Single Stage Monocular 6D Pose Estimation with Keypoint Enhancements [0.0]
  We present Yolo-Key-6D, a novel single stage, end-to-end framework for monocular 6D pose estimation.<n>Our approach enhances a YOLO based architecture by integrating an auxiliary head that regresses the 2D projections of an object's 3D bounding box corners.<n>YOLO-Key-6D achieves competitive accuracy scores of 96.24% and 69.41%, respectively, with the ADD(-S) 0.1d metric.
  arXiv  Detail & Related papers  (2026-03-04T09:31:07Z)
• Geo6DPose: Fast Zero-Shot 6D Object Pose Estimation via Geometry-Filtered Feature Matching [0.0]
  Geo6DPose is a lightweight, fully local, and training-free pipeline for zero-shot 6D pose estimation.<n>Geo6DPose achieves sub-second inference on a single commodity GPU while matching the average recall of significantly larger zero-shot baselines.
  arXiv  Detail & Related papers  (2025-12-11T14:20:17Z)
• RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery [72.13154206106259]
  We propose a novel pipeline that decouples the 6D pose and size estimation to mitigate the influence of imperfect scales on rigid transformations. Specifically, we leverage a pre-trained monocular estimator to extract local geometric information. A separate branch is designed to directly recover the metric scale of the object based on category-level statistics.
  arXiv  Detail & Related papers  (2023-09-19T02:20:26Z)
• CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformers [51.142988196855484]
  This paper introduces a novel method we call Cascaded Refinement Transformers, or CRT-6D. We replace the commonly used dense intermediate representation with a sparse set of features sampled from the feature pyramid we call Os(Object Keypoint Features) where each element corresponds to an object keypoint. We achieve inferences 2x faster than the closest real-time state of the art methods while supporting up to 21 objects on a single model.
  arXiv  Detail & Related papers  (2022-10-21T04:06:52Z)
• ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework [19.759108851254844]
  This framework is designed in a simple architecture that efficiently extracts point-wise features from RGB-D data using a fully convolutional network, called XYZNet. Experiments on YCB-Video and T-LESS datasets demonstrate the proposed framework's substantially superior performance in top accuracy and low computational cost.
  arXiv  Detail & Related papers  (2022-04-03T14:04:14Z)
• FS6D: Few-Shot 6D Pose Estimation of Novel Objects [116.34922994123973]
  6D object pose estimation networks are limited in their capability to scale to large numbers of object instances. In this work, we study a new open set problem; the few-shot 6D object poses estimation: estimating the 6D pose of an unknown object by a few support views without extra training.
  arXiv  Detail & Related papers  (2022-03-28T10:31:29Z)
• SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation [98.83762558394345]
  SO-Pose is a framework for regressing all 6 degrees-of-freedom (6DoF) for the object pose in a cluttered environment from a single RGB image. We introduce a novel reasoning about self-occlusion, in order to establish a two-layer representation for 3D objects. Cross-layer consistencies that align correspondences, self-occlusion and 6D pose, we can further improve accuracy and robustness.
  arXiv  Detail & Related papers  (2021-08-18T19:49:29Z)
• Spatial Attention Improves Iterative 6D Object Pose Estimation [52.365075652976735]
  We propose a new method for 6D pose estimation refinement from RGB images. Our main insight is that after the initial pose estimate, it is important to pay attention to distinct spatial features of the object. We experimentally show that this approach learns to attend to salient spatial features and learns to ignore occluded parts of the object, leading to better pose estimation across datasets.
  arXiv  Detail & Related papers  (2021-01-05T17:18:52Z)

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.