Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics

• URL: http://arxiv.org/abs/2501.07100v1
• Date: Mon, 13 Jan 2025 07:26:05 GMT
• Title: Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics
• Authors: Tze Ho Elden Tse, Runyang Feng, Linfang Zheng, Jiho Park, Yixing Gao, Jihie Kim, Ales Leonardis, Hyung Jin Chang,
• Abstract summary: We propose to leverage superquadrics as an alternative 3D object representation to bounding boxes. We demonstrate their effectiveness on both template-free object reconstruction and action recognition tasks. We also study the compositionality of actions by considering a more challenging task where the training combinations of verbs and nouns do not overlap with the testing split.
• Score: 31.819336585007104
• License:
• Abstract: With the availability of egocentric 3D hand-object interaction datasets, there is increasing interest in developing unified models for hand-object pose estimation and action recognition. However, existing methods still struggle to recognise seen actions on unseen objects due to the limitations in representing object shape and movement using 3D bounding boxes. Additionally, the reliance on object templates at test time limits their generalisability to unseen objects. To address these challenges, we propose to leverage superquadrics as an alternative 3D object representation to bounding boxes and demonstrate their effectiveness on both template-free object reconstruction and action recognition tasks. Moreover, as we find that pure appearance-based methods can outperform the unified methods, the potential benefits from 3D geometric information remain unclear. Therefore, we study the compositionality of actions by considering a more challenging task where the training combinations of verbs and nouns do not overlap with the testing split. We extend H2O and FPHA datasets with compositional splits and design a novel collaborative learning framework that can explicitly reason about the geometric relations between hands and the manipulated object. Through extensive quantitative and qualitative evaluations, we demonstrate significant improvements over the state-of-the-arts in (compositional) action recognition.

Related papers

• GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding [53.42728468191711]
  Open-Vocabulary 3D object affordance grounding aims to anticipate action possibilities'' regions on 3D objects with arbitrary instructions. We propose GREAT (GeometRy-intEntion collAboraTive inference) for Open-Vocabulary 3D Object Affordance Grounding.
  arXiv  Detail & Related papers  (2024-11-29T11:23:15Z)
• Interpretable Action Recognition on Hard to Classify Actions [11.641926922266347]
  Humans recognise complex activities in video by recognising critical-temporal relations among explicitly recognised objects and parts. To mimic this we build on a model which uses positions of objects and hands, and their motions, to recognise the activity taking place. To improve this model we focussed on three of the most confused classes (for this model) and identified that the lack of 3D information was the major problem. A state-of-the-art object detection model was fine-tuned to determine the difference between "Container" and "NotContainer" in order to integrate object shape information into the existing object features.
  arXiv  Detail & Related papers  (2024-09-19T21:23:44Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution [49.10497573378427]
  Estimating the pose and shape of hands and objects under interaction finds numerous applications including augmented and virtual reality. Our algorithm is optimisation to object models, and it learns the physical rules governing hand-object interaction. Experiments using four widely-used benchmarks show that our framework achieves beyond state-of-the-art accuracy in 3D pose estimation, as well as recovers dense 3D hand and object shapes.
  arXiv  Detail & Related papers  (2022-04-27T17:00:54Z)
• What's in your hands? 3D Reconstruction of Generic Objects in Hands [49.12461675219253]
  Our work aims to reconstruct hand-held objects given a single RGB image. In contrast to prior works that typically assume known 3D templates and reduce the problem to 3D pose estimation, our work reconstructs generic hand-held object without knowing their 3D templates.
  arXiv  Detail & Related papers  (2022-04-14T17:59:02Z)
• SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition [35.4163266882568]
  We introduce Self-Supervised Learning Over Sets (SOS) to pre-train a generic Objects In Contact (OIC) representation model. Our OIC significantly boosts the performance of multiple state-of-the-art video classification models.
  arXiv  Detail & Related papers  (2022-04-10T23:27:19Z)
• Towards unconstrained joint hand-object reconstruction from RGB videos [81.97694449736414]
  Reconstructing hand-object manipulations holds a great potential for robotics and learning from human demonstrations. We first propose a learning-free fitting approach for hand-object reconstruction which can seamlessly handle two-hand object interactions.
  arXiv  Detail & Related papers  (2021-08-16T12:26:34Z)
• VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects [19.296344218177534]
  The space of 3D articulated objects is exceptionally rich in their myriad semantic categories, diverse shape geometry, and complicated part functionality. Previous works mostly abstract kinematic structure with estimated joint parameters and part poses as the visual representations for manipulating 3D articulated objects. We propose object-centric actionable visual priors as a novel perception-interaction handshaking point that the perception system outputs more actionable guidance than kinematic structure estimation.
  arXiv  Detail & Related papers  (2021-06-28T07:47:31Z)
• Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion [78.98074380040838]
  We propose to consider hand and object jointly in feature space and explore the reciprocity of the two branches. We employ an auxiliary depth estimation module to augment the input RGB image with the estimated depth map. Our approach significantly outperforms existing approaches in terms of the reconstruction accuracy of objects.
  arXiv  Detail & Related papers  (2020-06-28T09:50:25Z)

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.