GeoRoute: Geometry-Aware Hybrid Inference for Traffic Future-Frame Prediction
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of predicting future video frames in traffic scenes, which is hard because objects can appear blurry or move strangely over time. They propose a new way to improve predictions without retraining the model by using information from multiple past frames and adjusting for camera views. Their method keeps the background stable and focuses on moving objects more accurately. Tests on a traffic video benchmark show their approach works well compared to other top methods.
future-frame predictionvideo diffusion modelstemporal coherencegeometry driftdepth-layered renderingmotion predictionvision-language modelAI City Challengeinference-time refinementstructured traffic scenes
Authors
Khang Minh Le, Hieu Dinh Trung Pham, Luu Thanh Danh, Nam-Tien Le, Hieu Anh Ngo, Phuong Huu Vu Tran, Son Nguyen Minh Le, Nguyen Trong Nghia, Tu Tran Thi Cam, Huy Minh Nhat Nguyen, Cuong Tuan Nguyen
Abstract
Long-horizon future-frame prediction is important for autonomous driving, traffic surveillance, and intelligent transportation systems, yet remains challenging due to temporal ghosting, geometry drift, and inconsistent object motion. Recent latent video diffusion models have achieved impressive visual quality, but directly applying them to structured traffic scenes often leads to unstable geometry and degraded temporal coherence over extended horizons. We present a training-free inference framework that stabilizes reliable static structure in pretrained video predictions through multi-frame temporal context and view-conditioned routing. For front-camera videos, our method refines generated futures with a multi-frame depth-layered renderer that projects static geometry from observed history frames while preserving dynamic regions from the generative base model. For heterogeneous traffic views, a frozen vision-language model infers a coarse camera group from the observed clip and selects a specialized motion-based predictor. The framework requires neither retraining nor fine-tuning of the underlying video model and can be applied directly to pretrained generators. We validate the proposed framework on the AI City Challenge Track 5 benchmark, where our final system achieves competitive performance among the top-ranked teams. These results demonstrate that geometry-aware inference-time refinement and view-conditioned hybrid inference can improve static-geometry stability and low-level structural fidelity without changing the original model architecture.