paper-with-me

Papers

Single Level Feature-to-Feature Forecasting with Deformable Convolutions

2019-07-26 · Josip Šarić, Marin Oršić, Tonći Antunović, Sacha Vražić, Siniša Šegvić

Future anticipation is of vital importance in autonomous driving and other decision-making systems. We present a method to anticipate semantic segmentation of future frames in driving scenarios based on feature-to-feature forecasting. Our method is based on a semantic segmentation model without lateral connections within the upsampling path. Such design ensures that the forecasting addresses only the most abstract features on a very coarse resolution. We further propose to express feature-to-feature forecasting with deformable convolutions. This increases the modelling power due to being able to represent different motion patterns within a single feature map. Experiments show that our models with deformable convolutions outperform their regular and dilated counterparts while minimally increasing the number of parameters. Our method achieves state of the art performance on the Cityscapes validation set when forecasting nine timesteps into the future.

📄 PDF Abstract BibTeX arXiv:1907.11475

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingDecision MakingSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion

2021-01-26 · Josip Šarić, Sacha Vražić, Siniša Šegvić

Dense semantic forecasting anticipates future events in video by inferring pixel-level semantics of an unobserved future image. We present a novel approach that is applicable to various single-frame architectures and tas…

Future predictionPanoptic SegmentationregressionSegmentation+1

Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet

2022-07-09 · Shihao Zou, Yuanlu Xu, Chao Li, Lingni Ma 외

Multi-person pose understanding from RGB videos involves three complex tasks: pose estimation, tracking and motion forecasting. Intuitively, accurate multi-person pose estimation facilitates robust tracking, and robust t…

3D Pose EstimationMotion ForecastingMulti-Person Pose EstimationPose Estimation

SEMAGIC: Learning Semantically Consistent Deformable 3D Representations from In-the-Wild Images

2026-05-27 · Sky Cen, Wufei Ma, Guofeng Zhang, Alan Yuille 외 arxiv

Learning deformable 3D object models from single-view in-the-wild images has enabled impressive 3D shape reconstruction without supervision. However, it remains unclear whether these models capture the semantic structure…

3D Shape ReconstructionSemantic correspondence

TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection

2026-08-27 · Su Wang, Yaochen Li, Min Yang, Jiaohao Nie 외 arxiv

Most single-stage 3D object detectors complete different tasks with the same extracted features. Nevertheless, it is impossible to project features into a common space that is adaptive for all the tasks. We present a nov…

3D Object Detection

Airport Passenger Flow Forecasting via Deformable Temporal-Spectral Transformer Approach

2025-12-04 · Wenbo Du, Lingling Han, Ying Xiong, Ling Zhang 외 arxiv

Accurate forecasting of passenger flows is critical for maintaining the efficiency and resilience of airport operations. Recent advances in patch-based Transformer models have shown strong potential in various time serie…

Time Series Forecasting