REVIEW 14 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
STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
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.
Forward citations
Cited by 14 Pith papers
-
PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
PointForward uses sparse world-space 3D queries and scene graphs to deliver consistent single-pass reconstruction of dynamic driving scenes via point-aligned representations.
-
ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes
ConFixGS repairs feedforward 3D Gaussian Splatting with confidence-aware diffusion priors, delivering up to 3.68 dB PSNR gains and halved FID scores on Waymo, nuScenes, and KITTI novel view synthesis tasks.
-
Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes
Ground4D resolves temporal conflicts in feedforward 4D Gaussian reconstruction for off-road scenes via voxel-grounded temporal aggregation with intra-voxel softmax and surface normal regularization, outperforming prio...
-
TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
TokenGS uses learnable Gaussian tokens in an encoder-decoder architecture to regress 3D means directly, achieving SOTA feed-forward reconstruction on static and dynamic scenes with better robustness.
-
FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images
A Transformer 3D-Gaussian model reconstructs incremental, animatable 4D head avatars from sparse portraits via alternating attention, sparse-to-dense UV densification, and residual motion refinement.
-
FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images
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.
-
Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving
Envision4D presents a feed-forward 4D Gaussian Splatting framework with future pose prediction, temporal attention, and conditioned motion lifting for pose-free extrapolation in autonomous driving scenes.
-
Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving
Xiaomi EV World Model integrates WorldRec for sparse-query 3D Gaussian reconstruction and WorldGen for fast causal video generation via bidirectional pretraining and causal fine-tuning to support autonomous driving si...
-
EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors
EnerGS introduces an energy-based soft guidance mechanism for partial geometry in 3D Gaussian Splatting to improve reconstruction quality and reduce overfitting in sparse outdoor settings.
-
GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation
GaussianDWM uses 3D Gaussians with embedded linguistic features, language-guided sampling, and dual-condition generation for unified scene understanding and multi-modal output in driving world models.
-
Flux4D: Flow-based Unsupervised 4D Reconstruction
Flux4D reconstructs large-scale dynamic 4D scenes unsupervised by predicting moving 3D Gaussians from photometric losses and static regularization when trained across multiple scenes.
-
SimScale: Learning to Drive via Real-World Simulation at Scale
SimScale synthesizes unseen driving states from real logs via neural rendering and reactive environments, generates pseudo-expert trajectories, and shows that co-training on real plus simulated data improves planning ...
-
L2D2-GS: Learning to Densify for Feedforward Dynamic Gaussian Scene Reconstruction
L2D2-GS reformulates generalizable dynamic Gaussian reconstruction as iterative optimization with a self-supervised densification policy and geometric regularization, claiming SOTA fidelity and zero-shot generalizatio...
-
Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving
A unified system integrating sparse-query 3D Gaussian reconstruction with multi-stage causal video generation for autonomous driving world models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.