Fast Encoder-Based 3D from Casual Videos via Point Track Processing

• URL: http://arxiv.org/abs/2404.07097v2
• Date: Wed, 26 Jun 2024 20:09:12 GMT
• Title: Fast Encoder-Based 3D from Casual Videos via Point Track Processing
• Authors: Yoni Kasten, Wuyue Lu, Haggai Maron,
• Abstract summary: We present TracksTo4D, a learning-based approach that enables inferring 3D structure and camera positions from dynamic content originating from casual videos. TracksTo4D is trained in an unsupervised way on a dataset of casual videos. Experiments show that TracksTo4D can reconstruct a temporal point cloud and camera positions of the underlying video with accuracy comparable to state-of-the-art methods.
• Score: 22.563073026889324
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper addresses the long-standing challenge of reconstructing 3D structures from videos with dynamic content. Current approaches to this problem were not designed to operate on casual videos recorded by standard cameras or require a long optimization time. Aiming to significantly improve the efficiency of previous approaches, we present TracksTo4D, a learning-based approach that enables inferring 3D structure and camera positions from dynamic content originating from casual videos using a single efficient feed-forward pass. To achieve this, we propose operating directly over 2D point tracks as input and designing an architecture tailored for processing 2D point tracks. Our proposed architecture is designed with two key principles in mind: (1) it takes into account the inherent symmetries present in the input point tracks data, and (2) it assumes that the movement patterns can be effectively represented using a low-rank approximation. TracksTo4D is trained in an unsupervised way on a dataset of casual videos utilizing only the 2D point tracks extracted from the videos, without any 3D supervision. Our experiments show that TracksTo4D can reconstruct a temporal point cloud and camera positions of the underlying video with accuracy comparable to state-of-the-art methods, while drastically reducing runtime by up to 95\%. We further show that TracksTo4D generalizes well to unseen videos of unseen semantic categories at inference time.

Related papers

• TAPIP3D: Tracking Any Point in Persistent 3D Geometry [25.357437591411347]
  We introduce TAPIP3D, a novel approach for long-term 3D point tracking in monocular and RGB-D videos. TAPIP3D represents videos as camera-stabilized feature clouds, leveraging depth and camera motion information. Our results demonstrate that compensating for camera motion improves tracking performance.
  arXiv  Detail & Related papers  (2025-04-20T19:09:43Z)
• St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World [106.91539872943864]
  St4RTrack is a framework that simultaneously reconstructs and tracks dynamic video content in a world coordinate frame from RGB inputs. We predict both pointmaps at the same moment, in the same world, capturing both static and dynamic scene geometry. We establish a new extensive benchmark for world-frame reconstruction and tracking, demonstrating the effectiveness and efficiency of our unified, data-driven framework.
  arXiv  Detail & Related papers  (2025-04-17T17:55:58Z)
• Easi3R: Estimating Disentangled Motion from DUSt3R Without Training [48.87063562819018]
  We introduce Easi3R, a simple yet efficient training-free method for 4D reconstruction. Our approach applies attention adaptation during inference, eliminating the need for from-scratch pre-training or network fine-tuning. Our experiments on real-world dynamic videos demonstrate that our lightweight attention adaptation significantly outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-31T17:59:58Z)
• VGGT: Visual Geometry Grounded Transformer [61.37669770946458]
  VGGT is a feed-forward neural network that directly infers all key 3D attributes of a scene. Network achieves state-of-the-art results in multiple 3D tasks.
  arXiv  Detail & Related papers  (2025-03-14T17:59:47Z)
• SIRE: SE(3) Intrinsic Rigidity Embeddings [16.630400019100943]
  We introduce SIRE, a self-supervised method for motion discovery of objects and dynamic scene reconstruction from casual scenes. Our method trains an image encoder to estimate scene rigidity and geometry, supervised by a simple 4D reconstruction loss. Our findings suggest that SIRE can learn strong geometry and motion rigidity priors from video data, with minimal supervision.
  arXiv  Detail & Related papers  (2025-03-10T18:00:30Z)
• 3D-Aware Instance Segmentation and Tracking in Egocentric Videos [107.10661490652822]
  Egocentric videos present unique challenges for 3D scene understanding. This paper introduces a novel approach to instance segmentation and tracking in first-person video. By incorporating spatial and temporal cues, we achieve superior performance compared to state-of-the-art 2D approaches.
  arXiv  Detail & Related papers  (2024-08-19T10:08:25Z)
• Long-Term 3D Point Tracking By Cost Volume Fusion [2.3411633024711573]
  We propose the first deep learning framework for long-term point tracking in 3D that generalizes to new points and videos without requiring test-time fine-tuning. Our model integrates multiple past appearances and motion information via a transformer architecture, significantly enhancing overall tracking performance.
  arXiv  Detail & Related papers  (2024-07-18T09:34:47Z)
• TAPVid-3D: A Benchmark for Tracking Any Point in 3D [63.060421798990845]
  We introduce a new benchmark, TAPVid-3D, for evaluating the task of Tracking Any Point in 3D. This benchmark will serve as a guidepost to improve our ability to understand precise 3D motion and surface deformation from monocular video.
  arXiv  Detail & Related papers  (2024-07-08T13:28:47Z)
• Instance Tracking in 3D Scenes from Egocentric Videos [18.02107257369472]
  Egocentric sensors such as AR/VR devices capture human-object interactions and offer the potential to provide task-assistance. This capability requires instance tracking in real-world 3D scenes from egocentric videos (IT3DEgo) We introduce a new benchmark dataset, consisting of RGB and depth videos, per-frame camera pose, and instance-level annotations in both 2D camera and 3D world coordinates.
  arXiv  Detail & Related papers  (2023-12-07T08:18:35Z)
• PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking [90.29143475328506]
  We introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. We animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos.
  arXiv  Detail & Related papers  (2023-07-27T17:58:11Z)
• 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)
• Monocular Quasi-Dense 3D Object Tracking [99.51683944057191]
  A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform.
  arXiv  Detail & Related papers  (2021-03-12T15:30:02Z)
• 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)

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.