Pith. sign in

REVIEW 2 cited by

STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes

Not yet reviewed by Pith; the record is open.

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 2501.00602 v1 pith:TZNS5JZO submitted 2024-12-31 cs.CV cs.LG

classification cs.CVcs.LG
keywords dynamicreconstructionstormscenescenesmodeloptimizationoutdoor
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present STORM, a spatio-temporal reconstruction model designed for reconstructing dynamic outdoor scenes from sparse observations. Existing dynamic reconstruction methods often rely on per-scene optimization, dense observations across space and time, and strong motion supervision, resulting in lengthy optimization times, limited generalization to novel views or scenes, and degenerated quality caused by noisy pseudo-labels for dynamics. To address these challenges, STORM leverages a data-driven Transformer architecture that directly infers dynamic 3D scene representations--parameterized by 3D Gaussians and their velocities--in a single forward pass. Our key design is to aggregate 3D Gaussians from all frames using self-supervised scene flows, transforming them to the target timestep to enable complete (i.e., "amodal") reconstructions from arbitrary viewpoints at any moment in time. As an emergent property, STORM automatically captures dynamic instances and generates high-quality masks using only reconstruction losses. Extensive experiments on public datasets show that STORM achieves precise dynamic scene reconstruction, surpassing state-of-the-art per-scene optimization methods (+4.3 to 6.6 PSNR) and existing feed-forward approaches (+2.1 to 4.7 PSNR) in dynamic regions. STORM reconstructs large-scale outdoor scenes in 200ms, supports real-time rendering, and outperforms competitors in scene flow estimation, improving 3D EPE by 0.422m and Acc5 by 28.02%. Beyond reconstruction, we showcase four additional applications of our model, illustrating the potential of self-supervised learning for broader dynamic scene understanding.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    FFAvatar uses a Transformer-based 3D Gaussian model with alternating attention and sparse-to-dense learning to enable feed-forward, incremental reconstruction of animatable 4D head avatars from sparse portrait images.

  2. E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

    E3D-Bench compares 16 3D geometric foundation models on depth, reconstruction, pose, and view-synthesis tasks with a unified evaluation toolkit.

Pith tools