Sorry, you need to enable JavaScript to visit this website.

Focal stack image sequences can be regarded as successive frames of videos, which are densely captured by focusing on a stack of focal planes. This type of data is able to provide focus cues for display technologies. Before the displays on the user side, focal stack video is possibly corrupted during compression, storage and transmission chains, generating error frames on the decoder side. The error regions are difficult to be recovered due to the focal changes among frames.

With the rapid development of 3D vision applications such as autonomous driving and the dramatic increase of point cloud data, it becomes critical to efficiently compress 3D point clouds. Recently, point-based point cloud compression has attracted great attention due to its superior performance at low bit rates. However, lacking an efficient way to represent the local geometric correlation well, most existing methods can hardly extract fine local features accurately. Thus it’s difficult for them to obtain high-quality reconstruction of local geometry of point clouds.

The semantic information obtained from large-scale computation in image compression is not practical. To solve this problem, we propose an Attention Aggregation Mechanism (AAM) for learning-based image compression, which is able to aggregate attention map from multiple scales and facilitate information embedding.

High Efficiency Video Coding. (HEVC) is the product of a large collaborative effort from industry and academic community and reflects the new international standardization for digital video coding technology. Compression capability is the main goal behind the digital video compression technology. HEVC achieves this goal at the expense of dramatically increasing coding complexity. One such area of increased complexity is due to the use of a recursive quad-tree to partition every frame to various block sizes, a process called prediction mode.

If we quantize a block of n samples and then transmit information about quantization step size in the same bitstream, we may naturally expect such a code to be at least O(1/n) redundant. However, as we will show in this paper, this may not necessarily be true. Moreover, we prove that asymptotically, such codes can be as efficient as block codes without embedded step-size information. The proof relies on results from the Diophantine approximations theory. We discuss the significance of this finding for practical applications, such as the design of audio and video coding algorithms.

Few-shot object detection (FSOD) enables the detector to recognize novel objects only using limited training samples, which could greatly alleviate model’s dependency on data. Most existing methods include two training stages, namely base training and fine-tuning. However, the unlabeled novel instances in the base set were untouched in previous works, which can be re-used to enhance the FSOD performance. Thus, a new instance mining model is proposed in this paper to excavate the novel samples from the base set. The detector is thus fine-tuned again by these additional free novel instances.