paper-with-me

Optical Flow Estimation

10개 벤치마크 · 논문 2,218편 · 이 태스크의 논문 보기 →

Benchmarks

Sintel-clean

결과 29개

Sintel-final

결과 28개

KITTI 2015 (train)

결과 19개

KITTI 2015

결과 18개

KITTI 2012

결과 12개

Spring

결과 11개

Most implemented

Papers

FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation

2026-09-10 · Vladislav Bargatin, Alexander Yakovenko, Khaled Abud, Dmitriy Vatolin hf

Optical flow methods typically rely on task-specific inductive biases, such as correlation volumes, feature warping, and iterative refinement, among others, to reach high accuracy. While effective, such biases constrain …

Optical Flow Estimation

Lossy Event Compression: From Event Stream Distortion to Task Performance

2026-08-28 · Zahra Rezaee, Catarina Brites, João Ascenso arxiv

Event cameras generate asynchronous, sparse data streams with microsecond temporal resolution, but in moderate-to-high motion scenes they can produce as many as hundreds of millions of events per second, creating signifi…

Optical Flow EstimationVideo ReconstructionObject Detection

Physically Real-time Infrared Attack against Optical Flow Estimation Networks

2026-07-29 · Shen You, Wei Jiang, Jiarui Liu, Yijian Ye 외 arxiv

With the promising performance of deep neural networks on image-based tasks, different real-world applications such as autonomous driving and motion detection have become increasingly mature and relevant to human lives. …

Optical Flow EstimationAutonomous DrivingMotion Detection

Anticipatory Risk-Guided Reinforcement Learning for Safe Flight Through Dynamic Clutter

2026-07-26 · Yuchao Mei, Guohao Zhang, Luxia Ai, Haopeng Chen 외 arxiv

Safe quadrotor navigation in cluttered and dynamic environments depends not only on instantaneous geometric perception, but more critically on anticipating collision risks induced by relative motion. Conventional modular…

Optical Flow EstimationReinforcement LearningObject Tracking

On the Real-World Generalisability of Optical Flow Models

2026-07-11 · Petter Reijalt, Sander Gielisse, Rickard Karlsson, Jan van Gemert arxiv

Real-world deployment of vision models to broadly benefit society is arguably a main research objective. In optical flow, however, the difficulty to obtain the ground truth has focused research mainly on synthetic data a…

Optical Flow Estimation

FlowPainter: Inpainting Optical Flow via Confidence-Guided Completion

2026-07-11 · Yuang Meng, Chenyang Wu, Xianshun Liu, Chun-Le Guo 외 arxiv

Existing optical flow methods broadly follow two paradigms: iterative optimization and diffusion-based estimation. Iterative methods, exemplified by RAFT, achieve high accuracy through recurrent refinement, but remain ch…

Optical Flow Estimation

전체 2,218편 보기 →