SpatialTracker: Tracking Any 2D Pixels in 3D Space

• URL: http://arxiv.org/abs/2404.04319v1
• Date: Fri, 5 Apr 2024 17:59:25 GMT
• Title: SpatialTracker: Tracking Any 2D Pixels in 3D Space
• Authors: Yuxi Xiao, Qianqian Wang, Shangzhan Zhang, Nan Xue, Sida Peng, Yujun Shen, Xiaowei Zhou,
• Abstract summary: We propose to estimate point trajectories in 3D space to mitigate the issues caused by image projection. Our method, named SpatialTracker, lifts 2D pixels to 3D using monocular depth estimators. Tracking in 3D allows us to leverage as-rigid-as-possible (ARAP) constraints while simultaneously learning a rigidity embedding that clusters pixels into different rigid parts.
• Score: 71.58016288648447
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process, leading to occlusions and discontinuities in the 2D motion domain. While 2D motion can be intricate, we posit that the underlying 3D motion can often be simple and low-dimensional. In this work, we propose to estimate point trajectories in 3D space to mitigate the issues caused by image projection. Our method, named SpatialTracker, lifts 2D pixels to 3D using monocular depth estimators, represents the 3D content of each frame efficiently using a triplane representation, and performs iterative updates using a transformer to estimate 3D trajectories. Tracking in 3D allows us to leverage as-rigid-as-possible (ARAP) constraints while simultaneously learning a rigidity embedding that clusters pixels into different rigid parts. Extensive evaluation shows that our approach achieves state-of-the-art tracking performance both qualitatively and quantitatively, particularly in challenging scenarios such as out-of-plane rotation.

Related papers

• Tracking by 3D Model Estimation of Unknown Objects in Videos [122.56499878291916]
  We argue that this representation is limited and instead propose to guide and improve 2D tracking with an explicit object representation. Our representation tackles a complex long-term dense correspondence problem between all 3D points on the object for all video frames. The proposed optimization minimizes a novel loss function to estimate the best 3D shape, texture, and 6DoF pose.
  arXiv  Detail & Related papers  (2023-04-13T11:32:36Z)
• XDGAN: Multi-Modal 3D Shape Generation in 2D Space [60.46777591995821]
  We propose a novel method to convert 3D shapes into compact 1-channel geometry images and leverage StyleGAN3 and image-to-image translation networks to generate 3D objects in 2D space. The generated geometry images are quick to convert to 3D meshes, enabling real-time 3D object synthesis, visualization and interactive editing. We show both quantitatively and qualitatively that our method is highly effective at various tasks such as 3D shape generation, single view reconstruction and shape manipulation, while being significantly faster and more flexible compared to recent 3D generative models.
  arXiv  Detail & Related papers  (2022-10-06T15:54:01Z)
• DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images [15.712721653893636]
  DM-NeRF is among the first to simultaneously reconstruct, decompose, manipulate and render complex 3D scenes in a single pipeline. Our method can accurately decompose all 3D objects from 2D views, allowing any interested object to be freely manipulated in 3D space.
  arXiv  Detail & Related papers  (2022-08-15T14:32:10Z)
• 3D Visual Tracking Framework with Deep Learning for Asteroid Exploration [22.808962211830675]
  In this paper, we focus on the studied accurate and real-time method for 3D tracking. A new large-scale 3D asteroid tracking dataset is presented, including binocular video sequences, depth maps, and point clouds of diverse asteroids. We propose a deep-learning based 3D tracking framework, named as Track3D, which involves 2D monocular tracker and a novel light-weight amodal axis-aligned bounding-box network, A3BoxNet.
  arXiv  Detail & Related papers  (2021-11-21T04:14:45Z)
• Accelerate 3D Object Processing via Spectral Layout [1.52292571922932]
  We propose to embed the essential information in a 3D object into 2D space via spectral layout. The proposed method can achieve high quality 2D representations for 3D objects, which enables to use 2D-based methods to process 3D objects.
  arXiv  Detail & Related papers  (2021-10-25T03:18:37Z)
• FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection [78.00922683083776]
  It is non-trivial to make a general adapted 2D detector work in this 3D task. In this technical report, we study this problem with a practice built on fully convolutional single-stage detector. Our solution achieves 1st place out of all the vision-only methods in the nuScenes 3D detection challenge of NeurIPS 2020.
  arXiv  Detail & Related papers  (2021-04-22T09:35:35Z)
• Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation [87.54570024320354]
  State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space. We develop a 3D cylinder partition and a 3D cylinder convolution based framework, termed as Cylinder3D, which exploits the 3D topology relations and structures of driving-scene point clouds.
  arXiv  Detail & Related papers  (2020-08-04T13:56:19Z)
• Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation [57.11299763566534]
  We present a solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. We exploit 3D geometry to fuse input images into a unified latent representation of pose, which is disentangled from camera view-points. Our architecture then conditions the learned representation on camera projection operators to produce accurate per-view 2d detections.
  arXiv  Detail & Related papers  (2020-04-05T12:52:29Z)
• RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving [26.216609821525676]
  Most successful 3D detectors take the projection constraint from the 3D bounding box to the 2D box as an important component. Our method predicts the nine perspective keypoints of a 3D bounding box in image space, and then utilize the geometric relationship of 3D and 2D perspectives to recover the dimension, location, and orientation in 3D space. Our method is the first real-time system for monocular image 3D detection while achieves state-of-the-art performance on the KITTI benchmark.
  arXiv  Detail & Related papers  (2020-01-10T08:29:20Z)

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.