Temporal-Anchor3DLane: Enhanced 3D Lane Detection with Multi-Task Losses and LSTM Fusion

• URL: http://arxiv.org/abs/2512.11869v1
• Date: Fri, 05 Dec 2025 21:52:18 GMT
• Title: Temporal-Anchor3DLane: Enhanced 3D Lane Detection with Multi-Task Losses and LSTM Fusion
• Abstract summary: Temporal-Anchor3DLane is an enhanced 3D lane detection framework that extends Anchor3DLane with three key contributions.<n>A lightweight Temporal LSTM Fusion module aggregates per-anchor features across frames, replacing a heavier Transformer-style temporal fusion.<n>On OpenLane, Temporal-Anchor3DLane improves F1 by +6.2 and yields smoother temporal trajectories.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Monocular 3D lane detection remains challenging due to depth ambiguity, occlusion, and temporal instability across frames. Anchor-based approaches such as Anchor3DLane have demonstrated strong performance by regressing continuous 3D lane curves from multi-camera surround views. However, the baseline model still exhibits (i) sensitivity to regression outliers, (ii) weak supervision of global curve geometry, (iii) difficulty in balancing multiple loss terms, and (iv) limited exploitation of temporal continuity. We propose Temporal-Anchor3DLane, an enhanced 3D lane detection framework that extends Anchor3DLane with three key contributions: (1) a set of multi-task loss improvements, including Balanced L1 regression, Chamfer point-set distance, and uncertainty-based loss weighting, together with focal and Dice components for classification and visibility; (2) a lightweight Temporal LSTM Fusion module that aggregates per-anchor features across frames, replacing a heavier Transformer-style temporal fusion; and (3) ESCOP-style training refinements that couple curve-level supervision with temporal consistency. On OpenLane, Temporal-Anchor3DLane improves F1 by +6.2 and yields smoother temporal trajectories, showing that small architectural and loss refinements significantly enhance 3D lane robustness without extra sensors or scaling.

Related papers

• ASTRA: Asynchronous Spatio-Temporal Reconstruction via Trajectory Alignment [86.35109211408489]
  We propose ASTRA, a framework that introduces 2D motion trajectories as explicit, texture-agnostic supervision for asynchronous dynamic reconstruction.<n>ASTRA preserves high-frequency spatial details and sustains strong robustness even under severe asynchrony with up to 25-frame offsets, achieving approximately 1.4 dB PSNR improvement, reducing temporal-offset MAE by 54.0%, and nearly quadrupling the synchronization success rate.
  arXiv  Detail & Related papers  (2026-08-03T10:06:45Z)
• LiveLight: Real-time Streaming Video Relighting with Interactive Control [50.08584152649119]
  We present LiveLight, the first diffusion-based framework for real-time streaming video relighting with interactive 3D lighting control.<n>We overcome three critical challenges: effectively injecting dynamic 3D lighting into a diffusion model, maintaining high-fidelity generation under a low NFE budget, and facilitating continuous streaming for interactive control.<n>Experiments on real-world and synthetic benchmarks demonstrate that LiveLight achieves state-of-the-art relighting quality while running at real-time speed.
  arXiv  Detail & Related papers  (2026-08-03T06:45:00Z)
• NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction [25.145305440192875]
  Pose-Free Feed-forward 3D Gaussian Splatting has recently emerged as a powerful paradigm for fast scene reconstruction.<n>However, its performance degrades significantly in long image sequences due to cumulative camera pose estimation drift.<n>We propose a synergistic pose-free framework that explicitly couples geometry and appearance via a Raymap-Guided Coupling Module.
  arXiv  Detail & Related papers  (2026-07-08T09:02:18Z)
• TriTS: Time Series Forecasting from a Multimodal Perspective [8.124083509364981]
  Time series forecasting plays a pivotal role in critical sectors such as finance, energy, transportation, and meteorology.<n>We propose TriTS, a novel cross-modal disentanglement framework that projects 1D time series into time, frequency, and 2D-vision spaces.<n>TriTS achieves state-of-the-art (SOTA) performance, fundamentally outperforming existing vision-based forecasters by drastically reducing both parameter count and inference.
  arXiv  Detail & Related papers  (2026-04-17T23:43:45Z)
• Fast-SAM3D: 3Dfy Anything in Images but Faster [65.17322167628367]
  SAM3D enables scalable, open-world 3D reconstruction from complex scenes, yet its deployment is hindered by prohibitive inference latency.<n>We present textbfFast-SAM3D, a training-free framework that aligns computation with instantaneous generation complexity.
  arXiv  Detail & Related papers  (2026-02-05T04:27:59Z)
• Depth-Guided Metric-Aware Temporal Consistency for Monocular Video Human Mesh Recovery [28.9705779052755]
  We propose a comprehensive framework that achieves metric-aware temporal consistency through three synergistic components.<n>A Depth-Guided Multi-Scale Fusion module adaptively integrates geometric priors with RGB features via confidence-aware gating.<n>A Motion-Depth Aligned Refinement (MoDAR) module that enforces temporal coherence through cross-modal attention between motion dynamics and geometric cues.
  arXiv  Detail & Related papers  (2026-02-04T06:41:03Z)
• Model Optimization for Multi-Camera 3D Detection and Tracking [13.756560739163362]
  Outside-in multi-camera perception is increasingly important in indoor environments.<n>We evaluate Sparse4D, a query-based 3D detection and tracking framework.<n>We study reduced input frame rates, post-training quantization, transfer to the WILDTRACK benchmark, and Transformer Engine mixedprecision fine-tuning.
  arXiv  Detail & Related papers  (2026-01-31T01:51:30Z)
• SPARK: Scalable Real-Time Point Cloud Aggregation with Multi-View Self-Calibration [1.3537117504260623]
  SPARK is a self-calibrating real-time multi-camera point cloud reconstruction framework.<n>It produces stable point clouds in dynamic scenes while scaling linearly with the number of cameras.
  arXiv  Detail & Related papers  (2026-01-13T10:32:22Z)
• MoRel: Long-Range Flicker-Free 4D Motion Modeling via Anchor Relay-based Bidirectional Blending with Hierarchical Densification [10.799902862870288]
  MoRel is a novel framework for temporally consistent and memory-efficient modeling of long-range dynamic scenes.<n>Our approach mitigates temporal discontinuities and flickering artifacts.<n>It achieves temporally coherent and flicker-free long-range 4D reconstruction while maintaining bounded memory usage.
  arXiv  Detail & Related papers  (2025-12-10T02:49:09Z)
• DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-temporal Fusion [28.146811420532455]
  We introduce DVLO4D, a novel visual-LiDAR odometry framework that leverages sparse spatial-temporal fusion to enhance accuracy and robustness.<n>Our method has high efficiency, with an inference time of 82 ms, possessing the potential for the real-time deployment.
  arXiv  Detail & Related papers  (2025-09-07T11:43:11Z)
• LiDAR-BIND-T: Improved and Temporally Consistent Sensor Modality Translation and Fusion for Robotic Applications [2.112132378217468]
  This paper extends LiDAR-BIND, a modular multi-modal fusion framework that binds heterogeneous sensors (radar, sonar) to a LiDAR-defined latent space.<n>We introduce three contributions: (i) temporal embedding similarity that aligns consecutive latent representations, (ii) a motion-aligned transformation loss that matches displacement between predictions and ground truth LiDAR, and (iii) windowed temporal fusion using a specialised temporal module.
  arXiv  Detail & Related papers  (2025-09-06T14:21:27Z)
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts [80.32933059529135]
  Test-Time Adaptation (TTA) methods have emerged to adapt to target distributions during inference.<n>We propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD.<n>In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues.
  arXiv  Detail & Related papers  (2025-08-28T07:09:21Z)
• RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator [4.021926055330021]
  Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering.<n>We propose RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator, designed for efficient and temporally consistent video restoration under AT conditions.
  arXiv  Detail & Related papers  (2025-08-15T11:20:18Z)
• Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction [62.69089767730514]
  We present GDFusion, a temporal fusion method for vision-based 3D semantic occupancy prediction (VisionOcc)<n>It opens up the underexplored aspects of temporal fusion within the VisionOcc framework, focusing on both temporal cues and fusion strategies.
  arXiv  Detail & Related papers  (2025-04-17T14:05:33Z)
• SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data Pretraining [62.433137130087445]
  SuperFlow++ is a novel framework that integrates pretraining and downstream tasks using consecutive camera pairs.<n>We show that SuperFlow++ outperforms state-of-the-art methods across diverse tasks and driving conditions.<n>With strong generalizability and computational efficiency, SuperFlow++ establishes a new benchmark for data-efficient LiDAR-based perception in autonomous driving.
  arXiv  Detail & Related papers  (2025-03-25T17:59:57Z)
• On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation [56.97699793236174]
  We study two kinds of robust cross-view consistency in this paper. We exploit the temporal coherence in both depth feature space and 3D voxel space for self-supervised monocular depth estimation. Experimental results on several outdoor benchmarks show that our method outperforms current state-of-the-art techniques.
  arXiv  Detail & Related papers  (2022-09-19T03:46:13Z)
• Self-Supervised Multi-Frame Monocular Scene Flow [61.588808225321735]
  We introduce a multi-frame monocular scene flow network based on self-supervised learning. We observe state-of-the-art accuracy among monocular scene flow methods based on self-supervised learning.
  arXiv  Detail & Related papers  (2021-05-05T17:49:55Z)

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.