TRACER: Training-Free Closed-Loop Structured Inference for Traffic Accident Reconstruction

• URL: http://arxiv.org/abs/2606.25002v1
• Date: Tue, 23 Jun 2026 16:28:09 GMT
• Title: TRACER: Training-Free Closed-Loop Structured Inference for Traffic Accident Reconstruction
• Abstract summary: Traffic accident reconstruction is a forensic inverse problem that requires recovering physically consistent motion from sparse and heterogeneous evidence.<n>Here, we present TRACER, a training-free framework that formulates reconstruction as a closed-loop structured inference process.<n>Experiments on real-world accident data show that TRACER achieves improved geometric fidelity, velocity consistency, and collision accuracy over both data-driven and physics-based baselines.
• Score: 30.569426567956977
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traffic accident reconstruction is a forensic inverse problem that requires recovering physically consistent motion from sparse and heterogeneous evidence. Existing learning-based approaches predominantly optimize for semantic plausibility or visual realism, rather than quantitative agreement with measurable geometry and dynamics. Here, we present TRACER, a training-free framework that formulates reconstruction as a closed-loop structured inference process. Instead of directly generating dense trajectories, our framework constructs and iteratively refines event-anchored motion hypotheses under geometric, kinematic, and interaction constraints, guided by structured case memory and consistency-driven diagnosis. This design enables incremental, interpretable corrections when evidence is insufficient, making the accident reconstruction process more aligned with the workflow of human experts. Experiments on real-world accident data show that TRACER achieves improved geometric fidelity, velocity consistency, and collision accuracy over both data-driven and physics-based baselines.

Related papers

• High-Fidelity Industrial Crash Dynamics Prediction via Geometry-Aware Operator Learning with Memory-Efficient Low-Rank Attention [0.2174820084855635]
  We show that the GeoTransolver framework provides a viable solution for accurate, high-fidelity crash dynamics prediction at industrial scale.<n>One-shot, time-conditional, and autoregressive rollout strategies are shown to achieve state-of-the-art accuracy with significantly reduced training overhead and inference latency.<n>Our results highlight the practical viability of geometry-aware operator learning for high-fidelity surrogate modeling of complex, safety-critical automotive dynamics.
  arXiv  Detail & Related papers  (2026-05-26T23:15:53Z)
• Aerodynamic force reconstruction using physics-informed Gaussian processes [0.0]
  We introduce a machine learning approach designed to reconstruct the underlying aerodynamic loads from noisy measurements of structural dynamic responses.<n>The model avoids overfitting, eliminates the need for regularization schemes, and allows for the use of heterogeneous and multi-fidelity data.<n>Results show a strong agreement between true and predicted loads, particularly related to root mean squared errors, magnitude, phase angle and peak values of the signals.
  arXiv  Detail & Related papers  (2026-05-21T07:45:19Z)
• Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction [52.32112533846212]
  MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions.<n>We address this limitation by moving reconstruction to discrete multi-scale latent space and posing it as autoregressive next-acceleration-scale prediction.<n>We show that our approach delivers improved reconstruction performance across diverse sampling patterns under extreme undersampling.
  arXiv  Detail & Related papers  (2026-05-19T04:40:50Z)
• Machine Learning-Augmented Acceleration of Iterative Ptychographic Reconstruction [56.83110460392765]
  Iterative ptychographic reconstruction algorithms are widely used for coherent diffractive imaging.<n>We propose a machine learning-augmented approach that accelerates iterative ptychographic reconstruction.
  arXiv  Detail & Related papers  (2026-05-01T21:46:58Z)
• Learning physically grounded traffic accident reconstruction from public accident reports [12.882161839040883]
  We formulate accident reconstruction from publicly accessible reports and scene measurements as a parameterized multimodal learning problem.<n>We construct CISS-REC, a dataset of 6,217 real-world accident cases curated from the NHTSA Crash Investigation Sampling System.<n>Our method outperforms representative baselines on CISS-REC, achieving the strongest overall reconstruction fidelity.
  arXiv  Detail & Related papers  (2026-04-29T14:33:27Z)
• StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval [75.28673512571449]
  A key challenge in Continual Text-to-Video Retrieval is feature drift.<n>We propose StructAlign, a structured cross-modal alignment method for CTVR.<n>Our method consistently outperforms state-of-the-art continual retrieval approaches.
  arXiv  Detail & Related papers  (2026-01-28T13:34:44Z)
• Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance [61.41904916189093]
  We propose a novel diffusion-based framework for reconstructing 3D geometry of hand-held objects from monocular RGB images.<n>We use hand-object interaction as geometric guidance to ensure plausible hand-object interactions.
  arXiv  Detail & Related papers  (2025-08-25T17:11:53Z)
• Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport [58.6869774515413]
  This paper introduces imaging Knowledge-Informed Dynamic Optimal Transport (KIDOT), a novel dynamic optimal transport framework.<n>KIDOT learns from unpaired data by modeling reconstruction as a continuous evolution path from measurements to images, guided by an imaging knowledge-informed cost function and transport equation.<n>Experiments on MRI and CT reconstruction demonstrate KIDOT's superior performance.
  arXiv  Detail & Related papers  (2025-05-23T09:05:10Z)
• Learning to Align and Refine: A Foundation-to-Diffusion Framework for Occlusion-Robust Two-Hand Reconstruction [50.952228546326516]
  Two-hand reconstruction from monocular images faces persistent challenges due to complex and dynamic hand postures.<n>Existing approaches struggle with such alignment issues, often resulting in misalignment and penetration artifacts.<n>We propose a dual-stage Foundation-to-Diffusion framework that precisely align 2D prior guidance from vision foundation models.
  arXiv  Detail & Related papers  (2025-03-22T14:42:27Z)
• Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning [23.659451444973627]
  We present a Trajectory modeling framework (TrajCL) based on Causal Learning. TrajCL markedly enhances performance in trajectory classification tasks while showcasing superior generalization and interpretability.
  arXiv  Detail & Related papers  (2024-04-22T10:34:58Z)
• Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance [110.63037190641414]
  We propose to learn congestion patterns explicitly and devise a novel "Sense--Learn--Reason--Predict" framework. By decomposing the learning phases into two stages, a "student" can learn contextual cues from a "teacher" while generating collision-free trajectories. In experiments, we demonstrate that the proposed model is able to generate collision-free trajectory predictions in a synthetic dataset.
  arXiv  Detail & Related papers  (2021-03-26T02:42:33Z)

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.