Disentangled Point Diffusion for Precise Object Placement

• URL: http://arxiv.org/abs/2604.11793v1
• Date: Mon, 13 Apr 2026 17:55:47 GMT
• Title: Disentangled Point Diffusion for Precise Object Placement
• Abstract summary: TAX-DPD is a hierarchical, disentangled point diffusion framework that achieves state-of-the-art performance in placement precision.<n>We present results on a cloth-hanging task in simulation, indicating that our framework can further relax assumptions on object rigidity.
• Score: 11.869520755259657
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in robotic manipulation have highlighted the effectiveness of learning from demonstration. However, while end-to-end policies excel in expressivity and flexibility, they struggle both in generalizing to novel object geometries and in attaining a high degree of precision. An alternative, object-centric approach frames the task as predicting the placement pose of the target object, providing a modular decomposition of the problem. Building on this goal-prediction paradigm, we propose TAX-DPD, a hierarchical, disentangled point diffusion framework that achieves state-of-the-art performance in placement precision, multi-modal coverage, and generalization to variations in object geometries and scene configurations. We model global scene-level placements through a novel feed-forward Dense Gaussian Mixture Model (GMM) that yields a spatially dense prior over global placements; we then model the local object-level configuration through a novel disentangled point cloud diffusion module that separately diffuses the object geometry and the placement frame, enabling precise local geometric reasoning. Interestingly, we demonstrate that our point cloud diffusion achieves substantially higher accuracy than a prior approach based on SE(3)-diffusion, even in the context of rigid object placement. We validate our approach across a suite of challenging tasks in simulation and in the real-world on high-precision industrial insertion tasks. Furthermore, we present results on a cloth-hanging task in simulation, indicating that our framework can further relax assumptions on object rigidity.

Related papers

• ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimation [44.69407221741985]
  Category-level object pose estimation aims to predict the pose and size of arbitrary objects in specific categories.<n>Existing methods struggle with the inherent incompleteness of observed point clouds.<n>We propose ComPose, a novel unified framework that tightly integrates shape completion.
  arXiv  Detail & Related papers  (2026-05-25T08:10:06Z)
• IoUCert: Robustness Verification for Anchor-based Object Detectors [58.35703549470485]
  We introduce IoUCert, a novel formal verification framework designed specifically to overcome these bottlenecks in anchor-based object detection architectures.<n>We show that our method enables the robustness verification of realistic, anchor-based models including SSD, YOLOv2, and YOLOv3 variants against various input perturbations.
  arXiv  Detail & Related papers  (2026-03-03T14:36:46Z)
• 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)
• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• Occlusion-Aware 3D Hand-Object Pose Estimation with Masked AutoEncoders [29.274913619777088]
  We propose an occlusion-aware hand-object pose estimation method based on masked autoencoders, termed as HOMAE.<n>We integrate multi-scale features extracted from the decoder to predict a signed distance field (SDF), capturing both global context and fine-grained geometry.<n>Experiments on challenging DexYCB and HO3Dv2 benchmarks demonstrate that HOMAE achieves state-of-the-art performance in hand-object pose estimation.
  arXiv  Detail & Related papers  (2025-06-12T15:30:47Z)
• BOOTPLACE: Bootstrapped Object Placement with Detection Transformers [23.300369070771836]
  We introduce BOOTPLACE, a novel paradigm that formulates object placement as a placement-by-detection problem.<n> Experimental results on established benchmarks demonstrate BOOTPLACE's superior performance in object repositioning.
  arXiv  Detail & Related papers  (2025-03-27T21:21:20Z)
• Non-rigid Relative Placement through 3D Dense Diffusion [11.12190956406194]
  "Relative placement" is to predict the placement of one object in relation to another. Recent methods for relative placement have made tremendous progress towards data-efficient learning for robot manipulation. They have yet to represent deformable transformations, despite the ubiquity of non-rigid bodies in real world settings. We present a novel vision-based method to learn cross-displacement through dense diffusion.
  arXiv  Detail & Related papers  (2024-10-25T01:54:17Z)
• Imagining the Unseen: Generative Location Modeling for Object Placement [49.71690795831461]
  We develop a generative location model that learns to predict plausible bounding boxes for an object.<n>Our approach first tokenizes the image and target object class, then decodes bounding box coordinates through an autoregressive transformer.<n> Empirical evaluations reveal that our generative location model achieves superior placement accuracy on the OPA dataset.
  arXiv  Detail & Related papers  (2024-10-17T14:00:41Z)
• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation [18.011044932979143]
  3DUDA is a method capable of adapting to a nuisance-ridden target domain without 3D or depth data. We represent object categories as simple cuboid meshes, and harness a generative model of neural feature activations. We show that our method simulates fine-tuning on a global pseudo-labeled dataset under mild assumptions.
  arXiv  Detail & Related papers  (2024-01-19T17:48:05Z)
• Towards Self-Supervised Category-Level Object Pose and Size Estimation [121.28537953301951]
  This work presents a self-supervised framework for category-level object pose and size estimation from a single depth image. We leverage the geometric consistency residing in point clouds of the same shape for self-supervision.
  arXiv  Detail & Related papers  (2022-03-06T06:02:30Z)

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.