Linking vision and motion for self-supervised object-centric perception

• URL: http://arxiv.org/abs/2307.07147v1
• Date: Fri, 14 Jul 2023 04:21:05 GMT
• Title: Linking vision and motion for self-supervised object-centric perception
• Authors: Kaylene C. Stocking, Zak Murez, Vijay Badrinarayanan, Jamie Shotton, Alex Kendall, Claire Tomlin, Christopher P. Burgess
• Abstract summary: Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features. Traditionally these representations have been obtained via supervised learning, but this decouples perception from the downstream driving task and could harm generalization. We adapt a self-supervised object-centric vision model to perform object decomposition using only RGB video and the pose of the vehicle as inputs.
• Score: 16.821130222597155
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features. Traditionally these representations have been obtained via supervised learning, but this decouples perception from the downstream driving task and could harm generalization. In this work we adapt a self-supervised object-centric vision model to perform object decomposition using only RGB video and the pose of the vehicle as inputs. We demonstrate that our method obtains promising results on the Waymo Open perception dataset. While object mask quality lags behind supervised methods or alternatives that use more privileged information, we find that our model is capable of learning a representation that fuses multiple camera viewpoints over time and successfully tracks many vehicles and pedestrians in the dataset. Code for our model is available at https://github.com/wayveai/SOCS.

Related papers

• CarFormer: Self-Driving with Learned Object-Centric Representations [4.6058519836859135]
  We learn to place objects into slots with a slot attention model on BEV sequences. Based on these object-centric representations, we train a transformer to learn to drive as well as reason about the future of other vehicles.
  arXiv  Detail & Related papers  (2024-07-22T17:59:01Z)
• Estimation of Appearance and Occupancy Information in Birds Eye View from Surround Monocular Images [2.69840007334476]
  Birds-eye View (BEV) expresses the location of different traffic participants in the ego vehicle frame from a top-down view. We propose a novel representation that captures various traffic participants appearance and occupancy information from an array of monocular cameras covering 360 deg field of view (FOV) We use a learned image embedding of all camera images to generate a BEV of the scene at any instant that captures both appearance and occupancy of the scene.
  arXiv  Detail & Related papers  (2022-11-08T20:57:56Z)
• Masked World Models for Visual Control [90.13638482124567]
  We introduce a visual model-based RL framework that decouples visual representation learning and dynamics learning. We demonstrate that our approach achieves state-of-the-art performance on a variety of visual robotic tasks.
  arXiv  Detail & Related papers  (2022-06-28T18:42:27Z)
• SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation [101.55622133406446]
  We propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras. Specifically, we employ a joint network to process all the surrounding views and propose a cross-view transformer to effectively fuse the information from multiple views. In experiments, our method achieves the state-of-the-art performance on the challenging multi-camera depth estimation datasets.
  arXiv  Detail & Related papers  (2022-04-07T17:58:47Z)
• OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving [10.3540046389057]
  This work presents a multi-task visual perception network on unrectified fisheye images. It consists of six primary tasks necessary for an autonomous driving system. We demonstrate that the jointly trained model performs better than the respective single task versions.
  arXiv  Detail & Related papers  (2021-02-15T10:46:24Z)
• Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data Augmentation [77.60050239225086]
  We propose an effective training data generation process by fitting a 3D car model with dynamic parts to vehicles in real images. Our approach is fully automatic without any human interaction. We present a multi-task network for VUS parsing and a multi-stream network for VHI parsing.
  arXiv  Detail & Related papers  (2020-12-15T03:03:38Z)
• Self-supervised Human Detection and Segmentation via Multi-view Consensus [116.92405645348185]
  We propose a multi-camera framework in which geometric constraints are embedded in the form of multi-view consistency during training. We show that our approach outperforms state-of-the-art self-supervised person detection and segmentation techniques on images that visually depart from those of standard benchmarks.
  arXiv  Detail & Related papers  (2020-12-09T15:47:21Z)
• "What's This?" -- Learning to Segment Unknown Objects from Manipulation Sequences [27.915309216800125]
  We present a novel framework for self-supervised grasped object segmentation with a robotic manipulator. We propose a single, end-to-end trainable architecture which jointly incorporates motion cues and semantic knowledge. Our method neither depends on any visual registration of a kinematic robot or 3D object models, nor on precise hand-eye calibration or any additional sensor data.
  arXiv  Detail & Related papers  (2020-11-06T10:55:28Z)
• SoDA: Multi-Object Tracking with Soft Data Association [75.39833486073597]
  Multi-object tracking (MOT) is a prerequisite for a safe deployment of self-driving cars. We propose a novel approach to MOT that uses attention to compute track embeddings that encode dependencies between observed objects.
  arXiv  Detail & Related papers  (2020-08-18T03:40:25Z)
• MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views [60.538802124885414]
  We present Multi-View LidarNet (MVLidarNet), a two-stage deep neural network for multi-class object detection and drivable space segmentation. MVLidarNet is able to detect and classify objects while simultaneously determining the drivable space using a single LiDAR scan as input. We show results on both KITTI and a much larger internal dataset, thus demonstrating the method's ability to scale by an order of magnitude.
  arXiv  Detail & Related papers  (2020-06-09T21:28:17Z)

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.