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

• URL: http://arxiv.org/abs/2501.00602v1
• Date: Tue, 31 Dec 2024 18:59:58 GMT
• Title: STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
• Authors: Jiawei Yang, Jiahui Huang, Yuxiao Chen, Yan Wang, Boyi Li, Yurong You, Apoorva Sharma, Maximilian Igl, Peter Karkus, Danfei Xu, Boris Ivanovic, Yue Wang, Marco Pavone,
• Abstract summary: STORM is atemporal reconstruction model designed for reconstructing dynamic outdoor scenes from sparse observations. We show that STORM achieves precise dynamic scene reconstruction, surpassing state-of-the-art per-scene optimization methods. We also showcase four additional applications of our model, illustrating the potential of self-supervised learning for broader dynamic scene understanding.
• Score: 47.4799413169038
• License:
• 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.

Related papers

• 4D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitives [116.2042238179433]
  In this paper, we frame dynamic scenes as unconstrained 4D volume learning problems. We represent a target dynamic scene using a collection of 4D Gaussian primitives with explicit geometry and appearance features. This approach can capture relevant information in space and time by fitting the underlying photorealistic-temporal volume. Notably, our 4DGS model is the first solution that supports real-time rendering of high-resolution, novel views for complex dynamic scenes.
  arXiv  Detail & Related papers  (2024-12-30T05:30:26Z)
• 4D Gaussian Splatting with Scale-aware Residual Field and Adaptive Optimization for Real-time Rendering of Temporally Complex Dynamic Scenes [19.24815625343669]
  SaRO-GS is a novel dynamic scene representation capable of achieving real-time rendering. To handle temporally complex dynamic scenes, we introduce a Scale-aware Residual Field. Our method has demonstrated state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-09T08:44:19Z)
• Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos [101.48581851337703]
  We present BTimer, the first motion-aware feed-forward model for real-time reconstruction and novel view synthesis of dynamic scenes. Our approach reconstructs the full scene in a 3D Gaussian Splatting representation at a given target ('bullet') timestamp by aggregating information from all the context frames. Given a casual monocular dynamic video, BTimer reconstructs a bullet-time scene within 150ms while reaching state-of-the-art performance on both static and dynamic scene datasets.
  arXiv  Detail & Related papers  (2024-12-04T18:15:06Z)
• Urban4D: Semantic-Guided 4D Gaussian Splatting for Urban Scene Reconstruction [86.4386398262018]
  Urban4D is a semantic-guided decomposition strategy inspired by advances in deep 2D semantic map generation. Our approach distinguishes potentially dynamic objects through reliable semantic Gaussians. Experiments on real-world datasets demonstrate that Urban4D achieves comparable or better quality than previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-12-04T16:59:49Z)
• Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly Training for 4D Reconstruction [12.111389926333592]
  Current 3DGS-based streaming methods treat the Gaussian primitives uniformly and constantly renew the densified Gaussians. We propose a novel three-stage pipeline for iterative streamable 4D dynamic spatial reconstruction. Our method achieves state-of-the-art performance in online 4D reconstruction, demonstrating a 20% improvement in on-the-fly training speed, superior representation quality, and real-time rendering capability.
  arXiv  Detail & Related papers  (2024-11-22T10:47:47Z)
• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion [118.74385965694694]
  We present Motion DUSt3R (MonST3R), a novel geometry-first approach that directly estimates per-timestep geometry from dynamic scenes. By simply estimating a pointmap for each timestep, we can effectively adapt DUST3R's representation, previously only used for static scenes, to dynamic scenes. We show that by posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics.
  arXiv  Detail & Related papers  (2024-10-04T18:00:07Z)
• EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision [85.17951804790515]
  EmerNeRF is a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. It simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping. Our method achieves state-of-the-art performance in sensor simulation.
  arXiv  Detail & Related papers  (2023-11-03T17:59:55Z)

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.