Get Started
Home
Topics
Search
Library
Research questionHow should projection formats be chosen for efficient end-to-end neural compression of 360-degree video?Spherical video must be mapped to a two-dimensional format before compression, and that mapping changes spatial continuity, sampling, motion estimation, and coding efficiency. The most effective projection can therefore depend on how the codec represents motion and image structure.
AI
Computer Vision
Image & Video Processing
Research Paper
Technology
Latest papersRecent research connected to this question, newest first.Projection-Aware End-to-End Learned Video Compression for 360-Degree VideoEvidence covers seven JVET 360Lib projection formats, JVET test sequences, the scale-space flow neural compression model, multiple rate points, and projection-aware reconstruction. Results use PSNR, spherical PSNR, weighted spherical PSNR, and Bjøntegaard delta rate, with comparisons to 360Lib and the conventional HM-16.16 codec; conclusions are specific to these systems and test conditions.research paper · Sep 4, 2026
Related questions
How can neural video representation decoders reduce compute and memory use on resource-constrained devices without hurting reconstruction quality?How can real-time immersive point-cloud streaming reduce bandwidth and cryptographic latency without degrading reconstruction quality?How can implicit-neural video codecs decouple bitrate scalability from decoding complexity in one embedded bitstream?How can ultra-low-bitrate video compression preserve perceptual quality and temporal consistency while decoding in real time?