Multi-view video encoding and decoding

• Main Authors: MCKOWIAK, SLAWOMIR, STANKIEWICZ, ALLGARD, DOMANSKI MAREK, STANKOWSKI, YAKUB, GRAJEK, THOMAS, GRZELKA, ADAM, ROZEK SLAWOMIR
• Format: Patent
• Language: Chinese; English
• Published: 09.01.2024
• Subjects: ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PICTORIAL COMMUNICATION, e.g. TELEVISION

Multi-view video data encoding and/or decoding contemplates: feature detection of first image data associated with a first view to obtain a first set of features corresponding to the first view; performing feature detection on second image data related to the second view to obtain a second group of features corresponding to the second view; performing feature matching on the first group of features and the second group of features to identify regions with common features; second input image data is predicted based on regions having common characteristics to generate a residual data bitstream. 多视图视频数据编码和/或解码，考虑了：对与第一视图相关的第一图像数据进行特征检测，以获得对应于第一视图的第一组特征；对与第二视图相关的第二图像数据进行特征检测，以获得对应于第二视图的第二组特征；对第一组特征和第二组特征进行特征匹配，以识别具有共同特性的区域；基于具有共同特性的区域对第二输入图像数据进行预测，以生成残差数据比特流。