GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors

• URL: http://arxiv.org/abs/2608.12203v1
• Date: Wed, 12 Aug 2026 15:57:08 GMT
• Title: GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors
• Abstract summary: Generative models like Diffusion Models and Flow Matching have demonstrated remarkable capabilities in synthesizing high-fidelity driving videos.<n>We argue that this inefficiency stems from the prevailing reliance on a standard Gaussian source distribution, where consecutive frames are as independent Gaussian noise.<n>We propose GeoFlow, a novel framework designed to achieve efficient driving video generation by harnessing explicit geometric priors.
• Score: 27.10799700736534
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative models like Diffusion Models and Flow Matching have demonstrated remarkable capabilities in synthesizing high-fidelity driving videos, but are severely constrained by high inference latency due to the requirement of extensive sampling steps. We argue that this inefficiency stems from the prevailing reliance on a standard Gaussian source distribution, where consecutive frames are initialized as independent Gaussian noise. This paradigm disregards the rich spatiotemporal correlations inherent in driving videos, compelling the model to regenerate deterministic scene structures existing in previous frames from noise, which is both computationally redundant and prone to geometric inconsistency. To address this problem, we propose GeoFlow, a novel framework designed to achieve efficient driving video generation by harnessing explicit geometric priors. Instead of sampling from standard Gaussian noise, we leverage multi-view geometry and spatially-adaptive noise injection to construct a Geometry-Aligned Prior (GAP) distribution as starting point. This initialization bridges the gap between source distribution and data distribution, yielding a significantly straighter and shorter sampling trajectory. Extensive experiments demonstrate that GeoFlow can achieve remarkable efficiency of both training and inference: merely several hours of fine-tuning on baseline models can significantly boost few-step generation quality, while fully converged training drastically reduces number of inference steps required for state-of-the-art video generation.

Related papers

• One-Step Flow Matching for Generative Modeling of Path-Dependent Physical Fields [0.6445605125467574]
  Flow matching (FM) model based on a transformer backbone for high-resolution path-dependent stress field generation.<n>The proposed model operates within the latent space of a variational autoencoder (VAE) and formulates the simulation of plastic fields as a video synthesis task.
  arXiv  Detail & Related papers  (2026-06-22T01:45:59Z)
• Complexity-Balanced Diffusion Splitting [20.558008394592097]
  Complexity-Balanced Splitting (CBS) is a principled framework for temporal capacity allocation.<n>CBS partitions the diffusion timeline into segments of equal approximation burden.<n>CBS consistently improves quality without increasing per-step inference cost.
  arXiv  Detail & Related papers  (2026-06-04T17:57:15Z)
• Optimal Transport Flow Matching by Design [26.301026025241374]
  Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution.<n>We reformulate the problem by treating the prior as a design choice rather than a fixed input.<n>Our method reduces trajectory curvature by more than $2times$ compared to existing flow matching methods.
  arXiv  Detail & Related papers  (2026-06-02T18:00:05Z)
• FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching [68.01498128172214]
  We propose a novel but simple inference-time approach for long video generation that is architecture-agnostic and requires no additional training.<n>Our method generates long videos via overlapping sliding windows, where predicted clean samples from adjacent windows are blended via emphTweedie matching to enforce both textbfmanifold constraint and temporal consistency across overlap regions.<n>Our method generates videos several times longer than the native window length while outperforming both training-free and autoregressive baselines in temporal consistency and visual quality, and further extends to audio-video joint generation and text-to-3DGS without any
  arXiv  Detail & Related papers  (2026-05-20T08:55:37Z)
• RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO [53.38929612273108]
  Causal autoregressive video diffusion models support real-time streaming generation by extrapolating future chunks from previously generated content.<n>We introduce the Real-time Autoregressive Video Extrapolation Network (RAVEN), a training-time test framework that repacks each self rollout into an interleaved sequence of clean historical endpoints.
  arXiv  Detail & Related papers  (2026-05-14T17:59:30Z)
• STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows [35.05757953878183]
  STARFlow-V is a normalizing flow-based video generator with substantial benefits such as end-to-end learning, robust causal prediction, and native likelihood estimation.<n>Results present the first evidence, to our knowledge, that NFs are capable of high-quality autoregressive video generation.
  arXiv  Detail & Related papers  (2025-11-25T16:27:58Z)
• Uniform Discrete Diffusion with Metric Path for Video Generation [103.86033350602908]
  Continuous-space video generation has advanced rapidly, while discrete approaches lag behind due to error accumulation and long-duration inconsistency.<n>We present Uniform generative modeling and present Uniform pAth (URSA), a powerful framework that bridges the gap with continuous approaches for scalable video generation.<n>URSA consistently outperforms existing discrete methods and achieves performance comparable to state-of-the-art continuous diffusion methods.
  arXiv  Detail & Related papers  (2025-10-28T17:59:57Z)
• Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models [57.49136894315871]
  New paradigm of test-time scaling has yielded remarkable breakthroughs in reasoning models and generative vision models.<n>We propose one solution to the problem of integrating test-time scaling knowledge into a model during post-training.<n>We replace reward guided test-time noise optimization in diffusion models with a Noise Hypernetwork that modulates initial input noise.
  arXiv  Detail & Related papers  (2025-08-13T17:33:37Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
  Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
  arXiv  Detail & Related papers  (2023-04-22T15:32:59Z)
• Minimizing Trajectory Curvature of ODE-based Generative Models [45.89620603363946]
  Recent generative models, such as diffusion models, rectified flows, and flow matching, define a generative process as a time reversal of a fixed forward process. We present an efficient method of training the forward process to minimize the curvature of generative trajectories without any ODE/SDE simulation.
  arXiv  Detail & Related papers  (2023-01-27T21:52:03Z)

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.