SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Picking

• URL: http://arxiv.org/abs/2512.08430v1
• Date: Tue, 09 Dec 2025 09:58:35 GMT
• Title: SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Picking
• Authors: Nico Leuze, Maximilian Hoh, Samed Doğan, Nicolas R. -Peña, Alfred Schoettl,
• Abstract summary: We introduce a holistic depth-only 6D pose estimation approach that fuses multi-view depth maps into a fine-grained 3D point cloud.<n>Our framework operates fully sparse, enabling high-resolution representations to capture fine geometric details crucial for accurate pose estimation in clutter.<n>We validate our method on the recently published IPD and MV-YCB multi-view datasets, demonstrating competitive performance in heavily cluttered industrial and household bin picking scenarios.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurately recovering 6D poses in densely packed industrial bin-picking environments remain a serious challenge, owing to occlusions, reflections, and textureless parts. We introduce a holistic depth-only 6D pose estimation approach that fuses multi-view depth maps into either a fine-grained 3D point cloud in its vanilla version, or a sparse Truncated Signed Distance Field (TSDF). At the core of our framework lies a staged heatmap mechanism that yields scene-adaptive attention priors across different resolutions, steering computation toward foreground regions, thus keeping memory requirements at high resolutions feasible. Along, we propose a density-aware sparse transformer block that dynamically attends to (self-) occlusions and the non-uniform distribution of 3D data. While sparse 3D approaches has proven effective for long-range perception, its potential in close-range robotic applications remains underexplored. Our framework operates fully sparse, enabling high-resolution volumetric representations to capture fine geometric details crucial for accurate pose estimation in clutter. Our method processes the entire scene integrally, predicting the 6D pose via a novel per-voxel voting strategy, allowing simultaneous pose predictions for an arbitrary number of target objects. We validate our method on the recently published IPD and MV-YCB multi-view datasets, demonstrating competitive performance in heavily cluttered industrial and household bin picking scenarios.

Related papers

• Any6D: Model-free 6D Pose Estimation of Novel Objects [76.30057578269668]
  We introduce Any6D, a model-free framework for 6D object pose estimation.<n>It requires only a single RGB-D anchor image to estimate both the 6D pose and size of unknown objects in novel scenes.<n>We evaluate our method on five challenging datasets.
  arXiv  Detail & Related papers  (2025-03-24T13:46:21Z)
• AdaOcc: Adaptive-Resolution Occupancy Prediction [20.0994984349065]
  We introduce AdaOcc, a novel adaptive-resolution, multi-modal prediction approach. Our method integrates object-centric 3D reconstruction and holistic occupancy prediction within a single framework. In close-range scenarios, we surpass previous baselines by over 13% in IOU, and over 40% in Hausdorff distance.
  arXiv  Detail & Related papers  (2024-08-24T03:46:25Z)
• FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models [67.96827539201071]
  We propose a novel test-time optimization approach for 3D scene reconstruction. Our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.
  arXiv  Detail & Related papers  (2023-08-10T17:55:02Z)
• Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images [60.0898989456276]
  We present a new framework named Cas6D for few-shot 6DoF pose estimation that is generalizable and uses only RGB images. To address the false positives of target object detection in the extreme few-shot setting, our framework utilizes a self-supervised pre-trained ViT to learn robust feature representations. Experimental results on the LINEMOD and GenMOP datasets demonstrate that Cas6D outperforms state-of-the-art methods by 9.2% and 3.8% accuracy (Proj-5) under the 32-shot setting.
  arXiv  Detail & Related papers  (2023-06-13T07:45:42Z)
• Rigidity-Aware Detection for 6D Object Pose Estimation [60.88857851869196]
  Most recent 6D object pose estimation methods first use object detection to obtain 2D bounding boxes before actually regressing the pose. We propose a rigidity-aware detection method exploiting the fact that, in 6D pose estimation, the target objects are rigid. Key to the success of our approach is a visibility map, which we propose to build using a minimum barrier distance between every pixel in the bounding box and the box boundary.
  arXiv  Detail & Related papers  (2023-03-22T09:02:54Z)
• MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network [14.754297065772676]
  We present a novel multi-view 6D pose estimation method called MV6D. We base our approach on the PVN3D network that uses a single RGB-D image to predict keypoints of the target objects. In contrast to current multi-view pose detection networks such as CosyPose, our MV6D can learn the fusion of multiple perspectives in an end-to-end manner.
  arXiv  Detail & Related papers  (2022-08-01T23:34:43Z)
• 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)
• Learning Stereopsis from Geometric Synthesis for 6D Object Pose Estimation [11.999630902627864]
  Current monocular-based 6D object pose estimation methods generally achieve less competitive results than RGBD-based methods. This paper proposes a 3D geometric volume based pose estimation method with a short baseline two-view setting. Experiments show that our method outperforms state-of-the-art monocular-based methods, and is robust in different objects and scenes.
  arXiv  Detail & Related papers  (2021-09-25T02:55:05Z)
• 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)
• Generative Sparse Detection Networks for 3D Single-shot Object Detection [43.91336826079574]
  3D object detection has been widely studied due to its potential applicability to many promising areas such as robotics and augmented reality. Yet, the sparse nature of the 3D data poses unique challenges to this task. We propose Generative Sparse Detection Network (GSDN), a fully-convolutional single-shot sparse detection network.
  arXiv  Detail & Related papers  (2020-06-22T15:54:24Z)

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.