Recent progress in 3D scene representation, including Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), has enabled photorealistic rendering with real-time performance. Among these, 3DGS has gained attention due to its capability to represent complex scenes using Gaussian splats. However, this representation introduces significant storage challenges because each splat contains 59 attributes—far more than conventional point clouds. Efficient compression of these attributes, particularly rotation parameters, is essential for practical deployment.

Paper presents theoretical explanation for bi-directional optical flow technique in generic case. Both non-equal distance to reference frames and two reference frames from the same side of predicted frame are allowed. Dynamic range analysis during bi-directional optical flow calculations is provided. Limits for refinement motion vector are recommended.

SHVC is the scalable extension of the latest video coding standard High Efficiency Video Coding (HEVC) and spatial resampling process is inevitable module to support spatial scalability. This paper describes in details the resampling process, including both texture and motion data resampling in SHVC, and using experimental evidence, demonstrate their benefits in terms of coding efficiency.

This paper is devoted to Sample Adaptive Offset (SAO). This technique was recently added into High Efficiency Video Coding (HEVC) standard. The concept of SAO is to reduce sample distortion of a region by classifying the region samples into multiple categories, obtaining an offset for each category, and then adding the offset to each sample, where the classifier index and the offsets are coded in the bit stream.