Video Segmentation via Multiple Granularity Analysis
We introduce a Multiple Granularity Analysis framework for video segmentation in a coarse-to-fine manner. We cast video segmentation as a spatio-temporal superpixel labeling problem. Benefited from the bounding volume provided by off-the-shelf object trackers, we estimate the foreground/ background super-pixel labeling using the spatiotemporal multiple instance learning algorithm to obtain coarse foreground/background separation within the volume. We further refine the segmentation mask in the pixel level using the graph-cut model. Extensive experiments on benchmark video datasets demonstrate the superior performance of the proposed video segmentation algorithm.
Code (0)
등록된 구현이 없습니다.
Tasks
Multiple Instance LearningSegmentationVideo SegmentationVideo Semantic SegmentationSimilar Papers 제목 키워드 기반
Multi-Granularity Video Object Segmentation
Current benchmarks for video segmentation are limited to annotating only salient objects (i.e., foreground instances). Despite their impressive architectural designs, previous works trained on these benchmarks have strug…
ObjectSegmentationSemantic SegmentationVideo Object Segmentation+2Spectrum-guided Multi-granularity Referring Video Object Segmentation
Current referring video object segmentation (R-VOS) techniques extract conditional kernels from encoded (low-resolution) vision-language features to segment the decoded high-resolution features. We discovered that this c…
ObjectReferring Expression SegmentationReferring Video Object SegmentationSegmentation+3VideoSAM: Open-World Video Segmentation
Video segmentation is essential for advancing robotics and autonomous driving, particularly in open-world settings where continuous perception and object association across video frames are critical. While the Segment An…
Autonomous DrivingDecoderImage SegmentationObject+6Open-World Video Segmentation
While video segmentation has advanced rapidly on short clips and closed-set benchmarks, open-world video segmentation remains largely unexplored. The challenge is twofold: (1) existing methods are not designed to support…
Open-World Video SegmentationGeometric Context from Videos
We present a novel algorithm for estimating the broad 3D geometric structure of outdoor video scenes. Leveraging spatio-temporal video segmentation, we decompose a dynamic scene captured by a video into geometric classes…
SegmentationVideo SegmentationVideo Semantic Segmentation