Pith. sign in

REVIEW 5 cited by

St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.13152 v1 pith:WQLKEVI6 submitted 2025-04-17 cs.CV

Haiwen Feng , Junyi Zhang , Qianqian Wang , Yufei Ye , Pengcheng Yu , Michael J. Black , Trevor Darrell , Angjoo Kanazawa This is my paper
classification cs.CV
keywords reconstructiontrackingdynamicworldbenchmarkcorrespondencesframeframework
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Dynamic 3D reconstruction and point tracking in videos are typically treated as separate tasks, despite their deep connection. We propose St4RTrack, a feed-forward framework that simultaneously reconstructs and tracks dynamic video content in a world coordinate frame from RGB inputs. This is achieved by predicting two appropriately defined pointmaps for a pair of frames captured at different moments. Specifically, we predict both pointmaps at the same moment, in the same world, capturing both static and dynamic scene geometry while maintaining 3D correspondences. Chaining these predictions through the video sequence with respect to a reference frame naturally computes long-range correspondences, effectively combining 3D reconstruction with 3D tracking. Unlike prior methods that rely heavily on 4D ground truth supervision, we employ a novel adaptation scheme based on a reprojection loss. We establish a new extensive benchmark for world-frame reconstruction and tracking, demonstrating the effectiveness and efficiency of our unified, data-driven framework. Our code, model, and benchmark will be released.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    Introduces a new task of goal-conditioned 3D point motion forecasting along with a 1.16M-video dataset, a 111-category benchmark, and a model that outperforms baselines while transferring to robotics and video generation.

  2. Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks

    cs.CV 2025-11 unverdicted novelty 6.0 of 10

    DenseMarks learns a canonical 3D embedding space for human head images by training a Vision Transformer with contrastive loss on pairwise point tracks from in-the-wild videos, plus landmark and segmentation supervision.

  3. ViPE: Video Pose Engine for 3D Geometric Perception

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    ViPE estimates camera intrinsics, motion, and dense near-metric depth from uncalibrated videos, outperforming baselines on TUM and KITTI while releasing annotations for 96M frames across real and generated videos.

  4. Advances in 4D Representation: Geometry, Motion, and Interaction

    cs.CV 2025-10 conditional novelty 4.0 of 10

    A representation-centric survey of 4D generation and reconstruction, organized by geometry, motion, and interaction, with qualitative trade-off comparisons across seven representation families.

  5. Reconstructing 4D Spatial Intelligence: A Survey

    cs.CV 2025-07 accept novelty 4.0 of 10

    A review that classifies 4D scene reconstruction methods into five progressive levels: low-level cues, scene components, dynamic scenes, interactions, and physics.

Pith tools