OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields

• URL: http://arxiv.org/abs/2607.10840v1
• Date: Sun, 12 Jul 2026 17:05:18 GMT
• Title: OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields
• Abstract summary: We propose OmniX, a feed-forward 4D reconstruction framework that predicts dense 3D point trajectories for every pixel from videos with large camera motion.<n>By leveraging the sparse and low-rank structure of 3D motion, these tokens generate trajectory fields for all pixels across all images while efficiently preserving global interactions.
• Score: 69.80996430631079
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Previous feed-forward 4D reconstruction methods either predict per-frame static point clouds, ignoring foreground motion, or estimate point cloud trajectories while being limited to small camera motions. This restricts their ability to aggregate observations over time and reconstruct complete dynamic scenes under large viewpoint changes. To address this limitation, we propose OmniX, a feed-forward 4D reconstruction framework that predicts dense 3D point trajectories for every pixel from videos with large camera motion. OmniX decouples dynamic motion modeling from static geometry prediction and represents motion using a compact set of dynamic tokens. By leveraging the sparse and low-rank structure of 3D motion, these tokens generate trajectory fields for all pixels across all images while efficiently preserving global interactions. To facilitate training, we further build an automatic UE5-based 4D data engine and introduce a large-scale dataset containing 80K scenes and 1.28M multi-view videos with full geometric annotations. OmniX achieves state-of-the-art performance on dense 3D point trajectory prediction and 3D point tracking, while also demonstrating competitive results on video depth estimation and camera pose estimation.

Related papers

• Syn4D: A Multiview Synthetic 4D Dataset [92.50132053229817]
  3D reconstruction and tracking of dynamic scenes from monocular video remains an important open challenge in computer vision.<n>To address this limitation, we introduce Syn4D, a multiview synthetic dynamic scenes.<n>Key feature of Syn4D is the ability to unproject any pixel into 3D.
  arXiv  Detail & Related papers  (2026-05-06T17:59:55Z)
• Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels [67.36972154532761]
  Estimating the 3D trajectory of every pixel from a monocular video is crucial and promising for a comprehensive understanding of the 3D dynamics of videos.<n>Recent monocular 3D tracking works demonstrate impressive performance, but are limited to either tracking sparse points on the first frame or a slow optimization-based framework for dense tracking.<n>We propose a feedforward model, called Track4World, enabling an efficient holistic 3D tracking of every pixel in the world-centric coordinate system.
  arXiv  Detail & Related papers  (2026-03-03T03:45:43Z)
• C4D: 4D Made from 3D through Dual Correspondences [77.04731692213663]
  We introduce C4D, a framework that leverages temporal correspondences to extend existing 3D reconstruction formulation to 4D.<n>C4D captures two types of correspondences: short-term optical flow and long-term point tracking.<n>We train a dynamic-aware point tracker that provides additional mobility information.
  arXiv  Detail & Related papers  (2025-10-16T17:59:06Z)
• Trace Anything: Representing Any Video in 4D via Trajectory Fields [98.85848134960172]
  Trajectory Field is a dense mapping that assigns a continuous 3D trajectory function of time to each pixel in every frame.<n>We introduce Trace Anything, a neural network that predicts the entire trajectory field in a single feed-forward pass.<n>We trained the Trace Anything model on large-scale 4D data, including data from our new platform.
  arXiv  Detail & Related papers  (2025-10-15T17:59:04Z)
• Geometry-aware 4D Video Generation for Robot Manipulation [28.709339959536106]
  We propose a 4D video generation model that enforces multi-view 3D consistency of videos by supervising the model with cross-view pointmap alignment during training.<n>This geometric supervision enables the model to learn a shared 3D representation of the scene, allowing it to predict future video sequences from novel viewpoints.<n>Compared to existing baselines, our method produces more visually stable and spatially aligned predictions across multiple simulated and real-world robotic datasets.
  arXiv  Detail & Related papers  (2025-07-01T18:01:41Z)
• Easi3R: Estimating Disentangled Motion from DUSt3R Without Training [69.51086319339662]
  We introduce Easi3R, a simple yet efficient training-free method for 4D reconstruction.<n>Our approach applies attention adaptation during inference, eliminating the need for from-scratch pre-training or network fine-tuning.<n>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)

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.