Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Reference

• URL: http://arxiv.org/abs/2406.18453v1
• Date: Wed, 26 Jun 2024 16:01:10 GMT
• Title: Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Reference
• Authors: Yuan Gao, Yajing Luo, Junhong Wang, Kui Jia, Gui-Song Xia,
• Abstract summary: Humans can easily deduce the relative pose of an unseen object, without label/training, given only a single query-reference image pair. We propose a novel 3D generalizable relative pose estimation method by elaborating (i) with a 2.5D shape from an RGB-D reference, (ii) with an off-the-shelf differentiable, and (iii) with semantic cues from a pretrained model like DINOv2.
• Score: 62.99706119370521
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans can easily deduce the relative pose of an unseen object, without label/training, given only a single query-reference image pair. This is arguably achieved by incorporating (i) 3D/2.5D shape perception from a single image, (ii) render-and-compare simulation, and (iii) rich semantic cue awareness to furnish (coarse) reference-query correspondence. Existing methods implement (i) by a 3D CAD model or well-calibrated multiple images and (ii) by training a network on specific objects, which necessitate laborious ground-truth labeling and tedious training, potentially leading to challenges in generalization. Moreover, (iii) was less exploited in the paradigm of (ii), despite that the coarse correspondence from (iii) enhances the compare process by filtering out non-overlapped parts under substantial pose differences/occlusions. Motivated by this, we propose a novel 3D generalizable relative pose estimation method by elaborating (i) with a 2.5D shape from an RGB-D reference, (ii) with an off-the-shelf differentiable renderer, and (iii) with semantic cues from a pretrained model like DINOv2. Specifically, our differentiable renderer takes the 2.5D rotatable mesh textured by the RGB and the semantic maps (obtained by DINOv2 from the RGB input), then renders new RGB and semantic maps (with back-surface culling) under a novel rotated view. The refinement loss comes from comparing the rendered RGB and semantic maps with the query ones, back-propagating the gradients through the differentiable renderer to refine the 3D relative pose. As a result, our method can be readily applied to unseen objects, given only a single RGB-D reference, without label/training. Extensive experiments on LineMOD, LM-O, and YCB-V show that our training-free method significantly outperforms the SOTA supervised methods, especially under the rigorous Acc@5/10/15{\deg} metrics and the challenging cross-dataset settings.

Related papers

• MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation [8.840744039764092]
  We propose a single-shot approach to determining 6-DoF pose of an object with available 3D computer-aided design (CAD) model from a single RGB image. Our method, dubbed MRC-Net, comprises two stages. The first performs pose classification and renders the 3D object in the classified pose. The second stage performs regression to predict fine-grained residual pose within class.
  arXiv  Detail & Related papers  (2024-03-12T18:36:59Z)
• MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images [57.71600854525037]
  We propose a Fuse-Describe-Match strategy for 6D pose estimation from RGB-D images. MatchU is a generic approach that fuses 2D texture and 3D geometric cues for 6D pose prediction of unseen objects.
  arXiv  Detail & Related papers  (2024-03-03T14:01:03Z)
• FoundPose: Unseen Object Pose Estimation with Foundation Features [11.32559845631345]
  FoundPose is a model-based method for 6D pose estimation of unseen objects from a single RGB image. The method can quickly onboard new objects using their 3D models without requiring any object- or task-specific training.
  arXiv  Detail & Related papers  (2023-11-30T18:52:29Z)
• SSR-2D: Semantic 3D Scene Reconstruction from 2D Images [54.46126685716471]
  In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without using any 3D annotations. The key idea of our approach is to design a trainable model that employs both incomplete 3D reconstructions and their corresponding source RGB-D images. Our method achieves the state-of-the-art performance of semantic scene completion on two large-scale benchmark datasets MatterPort3D and ScanNet.
  arXiv  Detail & Related papers  (2023-02-07T17:47:52Z)
• RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video [76.86512780916827]
  We present the first real-time method for motion capture of skeletal pose and 3D surface geometry of hands from a single RGB camera. In order to address the inherent depth ambiguities in RGB data, we propose a novel multi-task CNN. We experimentally verify the individual components of our RGB two-hand tracking and 3D reconstruction pipeline.
  arXiv  Detail & Related papers  (2021-06-22T12:53:56Z)
• Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images [69.5662419067878]
  Grounding referring expressions in RGBD image has been an emerging field. We present a novel task of 3D visual grounding in single-view RGBD image where the referred objects are often only partially scanned due to occlusion. Our approach first fuses the language and the visual features at the bottom level to generate a heatmap that localizes the relevant regions in the RGBD image. Then our approach conducts an adaptive feature learning based on the heatmap and performs the object-level matching with another visio-linguistic fusion to finally ground the referred object.
  arXiv  Detail & Related papers  (2021-03-14T11:18:50Z)
• Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild [96.09941542587865]
  We present a novel 3D pose refinement approach based on differentiable rendering for objects of arbitrary categories in the wild. In this way, we precisely align 3D models to objects in RGB images which results in significantly improved 3D pose estimates. We evaluate our approach on the challenging Pix3D dataset and achieve up to 55% relative improvement compared to state-of-the-art refinement methods in multiple metrics.
  arXiv  Detail & Related papers  (2020-07-17T12:34:38Z)

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.