paper-with-me

Papers

GIFT: Generated Indoor video frames for Texture-less point tracking

2025-03-17 · Jianzheng Huang, Xianyu Mo, Ziling Liu, Jinyu Yang, Feng Zheng

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.

📄 PDF Abstract BibTeX arXiv:2503.12944

Code (0)

등록된 구현이 없습니다.

Tasks

Motion EstimationPoint TrackingVideo Editing

Similar Papers 제목 키워드 기반

GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding

2026-03-26 · Junpeng Ma, Sashuai Zhou, Guanghao Li, Xin Gao 외 arxiv

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

2014-05-01 · Karim M. Mohamed, Mohamed A. Ismail, Nagia M. Ghanem

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 Summarization

Strumming to the Beat: Audio-Conditioned Contrastive Video Textures

2021-04-06 · Medhini Narasimhan, Shiry Ginosar, Andrew Owens, Alexei A. Efros 외

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 Synthesis

Dense Piecewise Planar RGB-D SLAM for Indoor Environments

2017-08-01 · Phi-Hung Le, Jana Kosecka

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 Odometry

FeatureFlow: Robust Video Interpolation via Structure-to-Texture Generation

2020-06-01 · CVPR 2020 6 · Shurui Gui, Chaoyue Wang, Qihua Chen, Dacheng Tao

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