Compressing Piecewise Smooth Images with the Mumford-Shah Cartoon Model
원문 초록
Compressing piecewise smooth images is important for many data types such as depth maps in 3D videos or optic flow fields for motion compensation. Specialised codecs that rely on explicitly stored segmentations excel in this task since they preserve discontinuities between smooth regions. However, current approaches rely on ad hoc segmentations that lack a clean interpretation in terms of energy minimisation. As a remedy, we derive a generic region merging algorithm from the Mumford-Shah cartoon model. It adapts the segmentation to arbitrary reconstruction operators for the segment content. In spite of its conceptual simplicity, our framework can outperform previous segment-based compression methods as well as BPG by up to 3 dB.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation
PD-SORT: Occlusion-Robust Multi-Object Tracking Using Pseudo-Depth Cues
Unsupervised Training of a Dynamic Context-Aware Deep Denoising Framework for Low-Dose Fluoroscopic Imaging
Infrared Small Target Detection in Satellite Videos: A New Dataset and A Novel Recurrent Feature Refinement Framework
One Homography is All You Need: IMM-based Joint Homography and Multiple Object State Estimation
IM-MoCo: Self-supervised MRI Motion Correction using Motion-Guided Implicit Neural Representations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.