{"slug": "projection-aware-end-to-end-learned-video-compression-for-360-degree-video", "title": "Projection-Aware End-to-End Learned Video Compression for 360-Degree Video", "summary": "A new thesis from arXiv (2608.28689v1) finds that equirectangular and padded equirectangular projections deliver the highest compression efficiency for end-to-end learned 360-degree video compression using the scale-space flow model, outperforming cubemap-based and rhombic dodecahedron projections. The study, which evaluated seven JVET 360Lib projections on JVET test sequences, shows that projection efficiency is codec-dependent, as conventional HM-16.16 codecs favor cubemap-based formats like equi-angular and adjusted cubemap projections.", "body_md": "arXiv:2608.28689v1 Announce Type: new\nAbstract: 360-degree video supports immersive applications such as virtual reality, autonomous driving, and education. Because spherical content cannot be processed directly by conventional video codecs, it must first be mapped to a two-dimensional projection. Projection choice affects spatial continuity, sampling uniformity, motion estimation, and compression efficiency.\nThis thesis investigates how projection format influences end-to-end neural compression of 360-degree video. Seven formats supported by JVET 360Lib are evaluated using the scale-space flow model, JVET test sequences, and common test conditions. Each sequence is converted from its source equirectangular projection to a coding projection, compressed at multiple rate points, reconstructed, and converted back. Performance is assessed using PSNR, spherical PSNR, weighted spherical PSNR, and Bj{\\o}ntegaard delta rate. A differentiable pipeline combining projection conversion, neural compression, and inverse projection is also compared with 360Lib.\nResults show that equirectangular and padded equirectangular projections provide the highest compression efficiency with the scale-space flow model, while cubemap-based and rhombic dodecahedron projections are less effective. This differs from the conventional HM-16.16 codec, for which cubemap-based formats, particularly equi-angular and adjusted cubemap projections, outperform equirectangular formats. Neural models based on optical flow benefit from the spatial continuity of single-face projections, whereas block-based hybrid codecs better accommodate multi-face layouts. These findings show that projection efficiency is codec-dependent and provide guidance for selecting projections for learning-based 360-degree video compression.", "url": "https://wpnews.pro/news/projection-aware-end-to-end-learned-video-compression-for-360-degree-video", "canonical_source": "https://arxiv.org/abs/2608.28689", "published_at": "2026-09-01 04:00:00+00:00", "updated_at": "2026-09-01 04:22:45.331771+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision"], "entities": ["arXiv", "JVET 360Lib", "scale-space flow model", "HM-16.16"], "alternates": {"html": "https://wpnews.pro/news/projection-aware-end-to-end-learned-video-compression-for-360-degree-video", "markdown": "https://wpnews.pro/news/projection-aware-end-to-end-learned-video-compression-for-360-degree-video.md", "text": "https://wpnews.pro/news/projection-aware-end-to-end-learned-video-compression-for-360-degree-video.txt", "jsonld": "https://wpnews.pro/news/projection-aware-end-to-end-learned-video-compression-for-360-degree-video.jsonld"}}