REVIEW 10 cited by
DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
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
read the original abstract
Closed-loop simulation is essential for advancing end-to-end autonomous driving systems. Contemporary sensor simulation methods, such as NeRF and 3DGS, rely predominantly on conditions closely aligned with training data distributions, which are largely confined to forward-driving scenarios. Consequently, these methods face limitations when rendering complex maneuvers (e.g., lane change, acceleration, deceleration). Recent advancements in autonomous-driving world models have demonstrated the potential to generate diverse driving videos. However, these approaches remain constrained to 2D video generation, inherently lacking the spatiotemporal coherence required to capture intricacies of dynamic driving environments. In this paper, we introduce DriveDreamer4D, which enhances 4D driving scene representation leveraging world model priors. Specifically, we utilize the world model as a data machine to synthesize novel trajectory videos, where structured conditions are explicitly leveraged to control the spatial-temporal consistency of traffic elements. Besides, the cousin data training strategy is proposed to facilitate merging real and synthetic data for optimizing 4DGS. To our knowledge, DriveDreamer4D is the first to utilize video generation models for improving 4D reconstruction in driving scenarios. Experimental results reveal that DriveDreamer4D significantly enhances generation quality under novel trajectory views, achieving a relative improvement in FID by 32.1%, 46.4%, and 16.3% compared to PVG, S3Gaussian, and Deformable-GS. Moreover, DriveDreamer4D markedly enhances the spatiotemporal coherence of driving agents, which is verified by a comprehensive user study and the relative increases of 22.6%, 43.5%, and 15.6% in the NTA-IoU metric.
Forward citations
Cited by 10 Pith papers
-
muSync-GS: Physics-Synchronized Driving Video Synthesis for Weather and Geometric Road Hazards
muSync-GS couples weather and road-shape edits in driving videos to a calibrated vehicle-dynamics model, so the synthesized ego motion and telemetry change with the same controls that drive the visual edits.
-
Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation
A feed-forward model reconstructs a layered, simulation-ready 3D Gaussian world from multi-view driving video in ~1.5 s, with quality approaching per-scene optimized reconstruction.
-
No Redundancy, No Stall: Lightweight Streaming 3D Gaussian Splatting for Real-time Rendering
A training-free 3DGS acceleration framework using tile warping, depth-based early-stop prediction, and load-balanced streaming hardware that reports 5.41x to 17.3x speedups.
-
WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration
A pipeline that restores corrupted novel-view videos with a video diffusion model and jointly denoises multiple viewpoints to improve 3D scene exploration from a single image.
-
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
Post-trained Cosmos world models generate controllable multi-view driving videos and LiDAR; augmenting real AV training data with these synthetic clips improves downstream perception and policy metrics, especially in ...
-
GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control
GeoDrive conditions a frozen video diffusion model on a 3D-rendered version of the requested ego trajectory, cutting trajectory-following error by 42% versus Vista while using 99.7% less training data.
-
Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method
UniScenev2 scales occupancy-centric driving-scene generation to NuPlan scale, releasing a 3.6M-frame semantic-occupancy dataset and jointly generating occupancy, video, and LiDAR that beats published baselines on its ...
-
I2V-GS: Infrastructure-to-Vehicle View Transformation with Gaussian Splatting for Autonomous Driving Data Generation
I2V-GS transforms infrastructure camera views into realistic vehicle views for autonomous driving training via Gaussian Splatting with adaptive depth warping and cascade diffusion inpainting.
-
EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling
A Real2Sim2Real framework that aligns simulator dynamics via differentiable parameter fitting and renders photorealistic policy-training videos with a diffusion model, improving real-world manipulation success.
-
Generative AI for Autonomous Driving: A Review
A review of generative models (VAEs, GANs, diffusion, transformers, LLMs) applied to map generation, scenario generation, trajectory prediction, and motion planning for autonomous driving.
Discussion (0). Sign in to comment.