Papers with Code 아카이브
Point Tracking
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 8
- 보존된 평가 기록
- 15
Point Tracking, often referred to as Tracking any Point (TAP) involves acquiring, focusing on, and continuously tracking specific target point/points across video frames. The system identifies the target point, maintains focus, and predicts its movement, enabling smooth tracking even if the target moves unpredictably, or through occlusions. TAP has wide applications like object tracking, surveillance, and autonomous navigation.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
SpatialTrackerV2: 3D Point Tracking Made Easy
CharaConsist: Fine-Grained Consistent Character Generation
MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second
Learning to Track Any Points from Human Motion
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model
You Are Your Best Teacher: Semi-Supervised Surgical Point Tracking with Cycle-Consistent Self-Distillation
TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion
Seurat: From Moving Points to Depth
TAPIP3D: Tracking Any Point in Persistent 3D Geometry
St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
TAPNext: Tracking Any Point (TAP) as Next Token Prediction
POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction
Point Tracking in Surgery--The 2024 Surgical Tattoos in Infrared (STIR) Challenge
Endo-TTAP: Robust Endoscopic Tissue Tracking via Multi-Facet Guided Attention and Hybrid Flow-point Supervision
Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
Toward Scalable, Flexible Scene Flow for Point Clouds
GIFT: Generated Indoor video frames for Texture-less point tracking
VGGT: Visual Geometry Grounded Transformer
Low Complexity Point Tracking of the Myocardium in 2D Echocardiography
Online Dense Point Tracking with Streaming Memory
A Training-Free Framework for Precise Mobile Manipulation of Small Everyday Objects
Pre-training Auto-regressive Robotic Models with 4D Representations
Control Barrier Function-Based Quadratic Programming for SafeOperation of Tethered UAVs
Track-On: Transformer-based Online Point Tracking with Memory
MATCHA:Towards Matching Anything
Exploring Temporally-Aware Features for Point Tracking
ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking
GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking
Microcontroller-Driven MPPT System for Enhanced Photovoltaic Efficiency: An Experimental Approach in Nepal
Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation
EgoPoints: Advancing Point Tracking for Egocentric Videos
Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmark
TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.