TrajLoom: Dense Future Trajectory Generation from Video

• URL: http://arxiv.org/abs/2603.22606v1
• Date: Mon, 23 Mar 2026 22:10:58 GMT
• Title: TrajLoom: Dense Future Trajectory Generation from Video
• Abstract summary: We propose a framework that predicts future trajectories and trajectories from past video context.<n>Compared with state-of-the-art methods our approach extends the prediction horizon from 24 to 81 frames.<n>The predicted trajectories directly support downstream video generation and editing.
• Score: 17.78215938363174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Predicting future motion is crucial in video understanding and controllable video generation. Dense point trajectories are a compact, expressive motion representation, but modeling their future evolution from observed video remains challenging. We propose a framework that predicts future trajectories and visibility from past trajectories and video context. Our method has three components: (1) Grid-Anchor Offset Encoding, which reduces location-dependent bias by representing each point as an offset from its pixel-center anchor; (2) TrajLoom-VAE, which learns a compact spatiotemporal latent space for dense trajectories with masked reconstruction and a spatiotemporal consistency regularizer; and (3) TrajLoom-Flow, which generates future trajectories in latent space via flow matching, with boundary cues and on-policy K-step fine-tuning for stable sampling. We also introduce TrajLoomBench, a unified benchmark spanning real and synthetic videos with a standardized setup aligned with video-generation benchmarks. Compared with state-of-the-art methods, our approach extends the prediction horizon from 24 to 81 frames while improving motion realism and stability across datasets. The predicted trajectories directly support downstream video generation and editing. Code, model checkpoints, and datasets are available at https://trajloom.github.io/.

Related papers

• GeoRoute: Geometry-Aware Hybrid Inference for Traffic Future-Frame Prediction [0.8091286187898472]
  Long-horizon future-frame prediction is important for autonomous driving, traffic surveillance, and intelligent transportation systems.<n>Recent latent video diffusion models have achieved impressive visual quality, but directly applying them to structured traffic scenes often leads to unstable geometry.<n>We present a training-free inference framework that stabilizes reliable static structure in pretrained video predictions.
  arXiv  Detail & Related papers  (2026-08-10T12:01:18Z)
• Geo-Align: Video Generation Alignment via Metric Geometry Reward [53.65904111864641]
  Geo-Align is the first Reinforcement Learning framework specifically designed for camera-controlled video re-rendering.<n>Built upon a pretrained model, we optimize the model through a scale-aware perceptual reward mechanism.<n>Experiments demonstrate that Geo-Align consistently outperforms existing supervised learning baselines in both precise camera controllability and visual fidelity.
  arXiv  Detail & Related papers  (2026-05-22T17:59:43Z)
• 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)
• Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better [61.381599921020175]
  Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts.<n>Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion.<n>We propose the Tracktention Layer, a novel architectural component that explicitly integrates motion information using point tracks.
  arXiv  Detail & Related papers  (2025-03-25T17:58:48Z)
• 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)
• Minimum Latency Deep Online Video Stabilization [77.68990069996939]
  We present a novel camera path optimization framework for the task of online video stabilization. In this work, we adopt recent off-the-shelf high-quality deep motion models for motion estimation to recover the camera trajectory. Our approach significantly outperforms state-of-the-art online methods both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2022-12-05T07:37:32Z)
• AutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points [92.91569287889203]
  We present a novel, label-free algorithm, AutoTrajectory, for trajectory extraction and prediction. To better capture the moving objects in videos, we introduce dynamic points. We aggregate dynamic points to instance points, which stand for moving objects such as pedestrians in videos.
  arXiv  Detail & Related papers  (2020-07-11T08:43:34Z)
• Future Video Synthesis with Object Motion Prediction [54.31508711871764]
  Instead of synthesizing images directly, our approach is designed to understand the complex scene dynamics. The appearance of the scene components in the future is predicted by non-rigid deformation of the background and affine transformation of moving objects. Experimental results on the Cityscapes and KITTI datasets show that our model outperforms the state-of-the-art in terms of visual quality and accuracy.
  arXiv  Detail & Related papers  (2020-04-01T16:09:54Z)

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.