SUGAR: Pre-training 3D Visual Representations for Robotics

• URL: http://arxiv.org/abs/2404.01491v1
• Date: Mon, 1 Apr 2024 21:23:03 GMT
• Title: SUGAR: Pre-training 3D Visual Representations for Robotics
• Authors: Shizhe Chen, Ricardo Garcia, Ivan Laptev, Cordelia Schmid,
• Abstract summary: We introduce a novel 3D pre-training framework for robotics named SUGAR. SUGAR captures semantic, geometric and affordance properties of objects through 3D point clouds. We show that SUGAR's 3D representation outperforms state-of-the-art 2D and 3D representations.
• Score: 85.55534363501131
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning generalizable visual representations from Internet data has yielded promising results for robotics. Yet, prevailing approaches focus on pre-training 2D representations, being sub-optimal to deal with occlusions and accurately localize objects in complex 3D scenes. Meanwhile, 3D representation learning has been limited to single-object understanding. To address these limitations, we introduce a novel 3D pre-training framework for robotics named SUGAR that captures semantic, geometric and affordance properties of objects through 3D point clouds. We underscore the importance of cluttered scenes in 3D representation learning, and automatically construct a multi-object dataset benefiting from cost-free supervision in simulation. SUGAR employs a versatile transformer-based model to jointly address five pre-training tasks, namely cross-modal knowledge distillation for semantic learning, masked point modeling to understand geometry structures, grasping pose synthesis for object affordance, 3D instance segmentation and referring expression grounding to analyze cluttered scenes. We evaluate our learned representation on three robotic-related tasks, namely, zero-shot 3D object recognition, referring expression grounding, and language-driven robotic manipulation. Experimental results show that SUGAR's 3D representation outperforms state-of-the-art 2D and 3D representations.

Related papers

• 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)
• Volumetric Environment Representation for Vision-Language Navigation [66.04379819772764]
  Vision-language navigation (VLN) requires an agent to navigate through a 3D environment based on visual observations and natural language instructions. We introduce a Volumetric Environment Representation (VER), which voxelizes the physical world into structured 3D cells. VER predicts 3D occupancy, 3D room layout, and 3D bounding boxes jointly.
  arXiv  Detail & Related papers  (2024-03-21T06:14:46Z)
• Object Scene Representation Transformer [56.40544849442227]
  We introduce Object Scene Representation Transformer (OSRT), a 3D-centric model in which individual object representations naturally emerge through novel view synthesis. OSRT scales to significantly more complex scenes with larger diversity of objects and backgrounds than existing methods. It is multiple orders of magnitude faster at compositional rendering thanks to its light field parametrization and the novel Slot Mixer decoder.
  arXiv  Detail & Related papers  (2022-06-14T15:40:47Z)
• 4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding [22.896937940702642]
  We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We propose a new data augmentation scheme leveraging synthetic 3D shapes moving in static 3D environments. Experiments demonstrate that our unsupervised representation learning results in improvement in downstream 3D semantic segmentation, object detection, and instance segmentation tasks.
  arXiv  Detail & Related papers  (2021-12-06T13:09:07Z)
• LanguageRefer: Spatial-Language Model for 3D Visual Grounding [72.7618059299306]
  We develop a spatial-language model for a 3D visual grounding problem. We show that our model performs competitively on visio-linguistic datasets proposed by ReferIt3D.
  arXiv  Detail & Related papers  (2021-07-07T18:55:03Z)
• Learning to Reconstruct and Segment 3D Objects [4.709764624933227]
  We aim to understand scenes and the objects within them by learning general and robust representations using deep neural networks. This thesis makes three core contributions from object-level 3D shape estimation from single or multiple views to scene-level semantic understanding.
  arXiv  Detail & Related papers  (2020-10-19T15:09:04Z)
• Weakly Supervised Learning of Multi-Object 3D Scene Decompositions Using Deep Shape Priors [69.02332607843569]
  PriSMONet is a novel approach for learning Multi-Object 3D scene decomposition and representations from single images. A recurrent encoder regresses a latent representation of 3D shape, pose and texture of each object from an input RGB image. We evaluate the accuracy of our model in inferring 3D scene layout, demonstrate its generative capabilities, assess its generalization to real images, and point out benefits of the learned representation.
  arXiv  Detail & Related papers  (2020-10-08T14:49:23Z)

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.