LSA: Localized Semantic Alignment for Enhancing Temporal Consistency in Traffic Video Generation

• URL: http://arxiv.org/abs/2602.05966v1
• Date: Thu, 05 Feb 2026 18:21:02 GMT
• Title: LSA: Localized Semantic Alignment for Enhancing Temporal Consistency in Traffic Video Generation
• Authors: Mirlan Karimov, Teodora Spasojevic, Markus Braun, Julian Wiederer, Vasileios Belagiannis, Marc Pollefeys,
• Abstract summary: Localized Semantic Alignment (LSA) is a framework for fine-tuning pre-trained video generation models.<n>LSA enhances temporal consistency by aligning semantic features between ground-truth and generated video clips.<n> experiments on nuScenes and KITTI datasets show the effectiveness of our approach.
• Score: 44.62533878314138
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Controllable video generation has emerged as a versatile tool for autonomous driving, enabling realistic synthesis of traffic scenarios. However, existing methods depend on control signals at inference time to guide the generative model towards temporally consistent generation of dynamic objects, limiting their utility as scalable and generalizable data engines. In this work, we propose Localized Semantic Alignment (LSA), a simple yet effective framework for fine-tuning pre-trained video generation models. LSA enhances temporal consistency by aligning semantic features between ground-truth and generated video clips. Specifically, we compare the output of an off-the-shelf feature extraction model between the ground-truth and generated video clips localized around dynamic objects inducing a semantic feature consistency loss. We fine-tune the base model by combining this loss with the standard diffusion loss. The model fine-tuned for a single epoch with our novel loss outperforms the baselines in common video generation evaluation metrics. To further test the temporal consistency in generated videos we adapt two additional metrics from object detection task, namely mAP and mIoU. Extensive experiments on nuScenes and KITTI datasets show the effectiveness of our approach in enhancing temporal consistency in video generation without the need for external control signals during inference and any computational overheads.

Related papers

• CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion [62.04833878126661]
  We tackle the dual challenges of video understanding and controllable video generation within a unified diffusion framework.<n>We propose CtrlVDiff, a unified diffusion model trained with a Hybrid Modality Control Strategy (HMCS) that routes and fuses features from depth, normals, segmentation, edges, and graphics-based intrinsics (albedo, roughness, metallic)<n>Across understanding and generation benchmarks, CtrlVDiff delivers superior controllability and fidelity, enabling layer-wise edits (relighting, material adjustment, object insertion) and surpassing state-of-the-art baselines while remaining robust when some modalities are unavailable.
  arXiv  Detail & Related papers  (2025-11-26T07:27:11Z)
• Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method [54.461213497603154]
  Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities.<n>Nuplan-Occ is the largest occupancy dataset to date, constructed from the widely used Nuplan benchmark.<n>We develop a unified framework that jointly synthesizes high-quality occupancy, multi-view videos, and LiDAR point clouds.
  arXiv  Detail & Related papers  (2025-10-27T03:52:45Z)
• Video Prediction of Dynamic Physical Simulations With Pixel-Space Spatiotemporal Transformers [3.951575888190684]
  This study investigates a transformer adaptation for video prediction with a simple end-to-end approach, comparing various selftemporal-attention layouts.<n>We introduce a simple yet effective transformer for autoregressive video prediction, utilizing continuous pixel-space representations for video prediction horizon.
  arXiv  Detail & Related papers  (2025-10-23T17:58:45Z)
• Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs [54.502280390499756]
  We propose TimeWarp to create a targeted synthetic temporal dataset to fine-tune the model's responses to encourage it to focus on the given input video.<n>We demonstrate that when our method is applied to existing models, it significantly improves performance on temporal understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-04T21:48:40Z)
• Motion-Aware Concept Alignment for Consistent Video Editing [57.08108545219043]
  We introduce MoCA-Video (Motion-Aware Concept Alignment in Video), a training-free framework bridging the gap between image-domain semantic mixing and video.<n>Given a generated video and a user-provided reference image, MoCA-Video injects the semantic features of the reference image into a specific object within the video.<n>We evaluate MoCA's performance using the standard SSIM, image-level LPIPS, temporal LPIPS, and introduce a novel metric CASS (Conceptual Alignment Shift Score) to evaluate the consistency and effectiveness of the visual shifts between the source prompt and the modified video frames
  arXiv  Detail & Related papers  (2025-06-01T13:28:04Z)
• Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models [34.131515004434846]
  We introduce Temporal In-Context Fine-Tuning (TIC-FT), an efficient approach for adapting pretrained video diffusion models to conditional generation tasks.<n>TIC-FT requires no architectural changes and achieves strong performance with as few as 10-30 training samples.<n>We validate our method across a range of tasks, including image-to-video and video-to-video generation, using large-scale base models such as CogVideoX-5B and Wan-14B.
  arXiv  Detail & Related papers  (2025-06-01T12:57:43Z)
• Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling [7.3949576464066]
  We propose a deep learning framework designed to significantly optimize bandwidth for motion-transfer-enabled video applications.<n>To capture complex motion effectively, we utilize the First Order Motion Model (FOMM), which encodes dynamic objects by detecting keypoints.<n>We validate our results across three datasets for video animation and reconstruction using the following metrics: Mean Absolute Error, Joint Embedding Predictive Architecture Embedding Distance, Structural Similarity Index, and Average Pair-wise Displacement.
  arXiv  Detail & Related papers  (2025-04-07T22:21:54Z)
• VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval [8.908777234657046]
  Large-language and vision-language models (LLM/LVLMs) have gained prominence across various domains.<n>Here we propose VideoLights, a novel HD/MR framework addressing these limitations through (i) Convolutional Projection and Feature Refinement modules.<n> Comprehensive experiments on QVHighlights, TVSum, and Charades-STA benchmarks demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-02T14:45:53Z)
• TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model [11.281386703572842]
  TimeDiT is a diffusion transformer model that combines temporal dependency learning with probabilistic sampling.<n>TimeDiT employs a unified masking mechanism to harmonize the training and inference process across diverse tasks.<n>Our systematic evaluation demonstrates TimeDiT's effectiveness both in fundamental tasks, i.e., forecasting and imputation, through zero-shot/fine-tuning.
  arXiv  Detail & Related papers  (2024-09-03T22:31:57Z)
• Self-Supervised Video Representation Learning via Latent Time Navigation [12.721647696921865]
  Self-supervised video representation learning aims at maximizing similarity between different temporal segments of one video. We propose Latent Time Navigation (LTN) to capture fine-grained motions. Our experimental analysis suggests that learning video representations by LTN consistently improves performance of action classification.
  arXiv  Detail & Related papers  (2023-05-10T20:06:17Z)
• Transform-Equivariant Consistency Learning for Temporal Sentence Grounding [66.10949751429781]
  We introduce a novel Equivariant Consistency Regulation Learning framework to learn more discriminative representations for each video. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted. In particular, we devise a self-supervised consistency loss module to enhance the completeness and smoothness of the augmented video.
  arXiv  Detail & Related papers  (2023-05-06T19:29:28Z)

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.