GIFT: Generated Indoor video frames for Texture-less point tracking
Point tracking is becoming a powerful solver for motion estimation and video editing. Compared to classical feature matching, point tracking methods have the key advantage of robustly tracking points under complex camera motion trajectories and over extended periods. However, despite certain improvements in methodologies, current point tracking methods still struggle to track any position in video frames, especially in areas that are texture-less or weakly textured. In this work, we first introduce metrics for evaluating the texture intensity of a 3D object. Using these metrics, we classify the 3D models in ShapeNet into three levels of texture intensity and create GIFT, a challenging synthetic benchmark comprising 1800 indoor video sequences with rich annotations. Unlike existing datasets that assign ground truth points arbitrarily, GIFT precisely anchors ground truth on classified target objects, ensuring that each video corresponds to a specific texture intensity level. Furthermore, we comprehensively evaluate current methods on GIFT to assess their performance across different texture intensity levels and analyze the impact of texture on point tracking.
Code (0)
등록된 구현이 없습니다.
Tasks
Motion EstimationPoint TrackingVideo EditingSimilar Papers 제목 키워드 기반
GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding
Video Large Language Models (VLMs) have achieved remarkable success in video understanding, but the significant computational cost from processing dense frames severely limits their practical application. Existing method…
VSCAN: An Enhanced Video Summarization using Density-based Spatial Clustering
In this paper, we present VSCAN, a novel approach for generating static video summaries. This approach is based on a modified DBSCAN clustering algorithm to summarize the video content utilizing both color and texture fe…
ClusteringVideo SummarizationStrumming to the Beat: Audio-Conditioned Contrastive Video Textures
We introduce a non-parametric approach for infinite video texture synthesis using a representation learned via contrastive learning. We take inspiration from Video Textures, which showed that plausible new videos could b…
Contrastive LearningSelf-Supervised LearningTexture SynthesisDense Piecewise Planar RGB-D SLAM for Indoor Environments
The paper exploits weak Manhattan constraints to parse the structure of indoor environments from RGB-D video sequences in an online setting. We extend the previous approach for single view parsing of indoor scenes to vid…
Visual OdometryFeatureFlow: Robust Video Interpolation via Structure-to-Texture Generation
Video interpolation aims to synthesize non-existent frames between two consecutive frames. Although existing optical flow based methods have achieved promising results, they still face great challenges in dealing with th…
Optical Flow EstimationTexture SynthesisVideo Frame Interpolation