pith. sign in

arxiv: 2503.15208 · v1 · pith:HS6GJMBNnew · submitted 2025-03-19 · 💻 cs.CV

DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation

classification 💻 cs.CV
keywords depthdist-4dmetricspatialdiffusiondrivinggeometricrepresentation
0
0 comments X
read the original abstract

Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization. A key challenge lies in finding an efficient and generalizable geometric representation that seamlessly connects temporal and spatial synthesis. To address this, we propose DiST-4D, the first disentangled spatiotemporal diffusion framework for 4D driving scene generation, which leverages metric depth as the core geometric representation. DiST-4D decomposes the problem into two diffusion processes: DiST-T, which predicts future metric depth and multi-view RGB sequences directly from past observations, and DiST-S, which enables spatial NVS by training only on existing viewpoints while enforcing cycle consistency. This cycle consistency mechanism introduces a forward-backward rendering constraint, reducing the generalization gap between observed and unseen viewpoints. Metric depth is essential for both accurate reliable forecasting and accurate spatial NVS, as it provides a view-consistent geometric representation that generalizes well to unseen perspectives. Experiments demonstrate that DiST-4D achieves state-of-the-art performance in both temporal prediction and NVS tasks, while also delivering competitive performance in planning-related evaluations.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation

    cs.CV 2026-05 unverdicted novelty 7.0

    A kinematic-to-visual lifting paradigm combined with hierarchically routed control generates action-conditioned surgical videos with better faithfulness, fidelity, and efficiency.

  2. Relit-LiVE: Relight Video by Jointly Learning Environment Video

    cs.CV 2026-05 unverdicted novelty 6.0

    Relit-LiVE jointly predicts relit videos and viewpoint-aligned environment maps inside a single diffusion process to achieve physically consistent video relighting without camera pose input.

  3. DriveLaW:Unifying Planning and Video Generation in a Latent Driving World

    cs.CV 2025-12 unverdicted novelty 6.0

    DriveLaW unifies video world modeling and trajectory planning by injecting video-generator latents into a diffusion planner, achieving SOTA video prediction and a new record on the NAVSIM planning benchmark.

  4. GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation

    cs.CV 2025-12 unverdicted novelty 6.0

    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.

  5. FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model

    cs.CV 2026-06 unverdicted novelty 5.0

    FrozenDrive enables zero-shot text-guided generation of consistent multi-view driving scenes via a parameter-free frozen diffusion backbone with spatio-temporal attention, improving autonomous driving models on advers...