https://github.com/cszhilu1998/selfdzsr_plusplus
공식 코드Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations
Papers with Code 아카이브
Optical Flow Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 10
- 보존된 평가 기록
- 133
Optical Flow Estimation is a computer vision task that involves computing the motion of objects in an image or a video sequence. The goal of optical flow estimation is to determine the movement of pixels or features in the image, which can be used for various applications such as object tracking, motion analysis, and video compression.
Approaches for optical flow estimation include correlation-based, block-matching, feature tracking, energy-based, and more recently gradient-based.
Further readings:
Definition source: Devon: Deformable Volume Network for Learning Optical Flow
Image credit: Optical Flow Estimation
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/cv-stuttgart/MS_RAFT_plus
공식 코드High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)
https://github.com/cv-stuttgart/ccmr
공식 코드CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning
https://github.com/cv-stuttgart/detectiondefenses
공식 코드Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow
https://github.com/cv-stuttgart/distractingdownpour
공식 코드Distracting Downpour: Adversarial Weather Attacks for Motion Estimation
https://github.com/cv-stuttgart/ms_raft
공식 코드Multi-Scale RAFT: Combining Hierarchical Concepts for Learning-based Optical FLow Estimation
https://github.com/cv-stuttgart/pcfa
공식 코드A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow
https://github.com/cv-stuttgart/sceneflow_from_blender
공식 코드Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo
https://github.com/cyf-cuber/mol
공식 코드https://github.com/dachunkai/ev-deblurvsr
공식 코드https://github.com/dakshitagrawal/nova
공식 코드NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects
https://github.com/dangeng/CorrWiseLosses
공식 코드Comparing Correspondences: Video Prediction with Correspondence-wise Losses
https://github.com/daniilidis-group/EV-FlowNet
공식 코드EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras
https://github.com/danqu130/DCEIFlow
공식 코드Learning Dense and Continuous Optical Flow from an Event Camera
https://github.com/danqu130/RPEFlow
공식 코드RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation
https://github.com/dasongli1/shift-net
공식 코드A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift
https://github.com/daveishan/timebalance
공식 코드https://github.com/dcharatan/flowmap
공식 코드FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent
https://github.com/deepcs233/TIN
공식 코드https://github.com/deepmind/brave
공식 코드https://github.com/deepmind/deepmind-research/tree/master/perceiver
공식 코드Perceiver IO: A General Architecture for Structured Inputs & Outputs
https://github.com/deepmind/tapnet
공식 코드https://github.com/denfed/heartheflow
공식 코드Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization
https://github.com/dfki-av/pwoc-3d
공식 코드PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation
https://github.com/dhyuan99/veckm_flow
공식 코드https://github.com/dlr-rm/granite
공식 코드Towards Robust Monocular Visual Odometry for Flying Robots on Planetary Missions
https://github.com/donglao/depthtosemantic
공식 코드On the Viability of Monocular Depth Pre-training for Semantic Segmentation
https://github.com/donnyyou/torchcv
공식 코드https://github.com/dqiaole/flowdiffusion_pytorch
공식 코드Open-DDVM: A Reproduction and Extension of Diffusion Model for Optical Flow Estimation
https://github.com/dqiaole/matchflow
공식 코드Rethinking Optical Flow from Geometric Matching Consistent Perspective
https://github.com/dqiaole/spot
공식 코드https://github.com/dreamscene4d/dreamscene4d
공식 코드DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
https://github.com/drinkingcoder/FlowFormer-Official
공식 코드https://github.com/duke-vision/optical-flow-active-learning-release
공식 코드Optical Flow Training under Limited Label Budget via Active Learning
https://github.com/duke-vision/semantic-unsup-flow-release
공식 코드SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving
https://github.com/dulucas/uvo_challenge
공식 코드UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place Solution
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.