all AI news
HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion. (arXiv:2305.06356v2 [cs.CV] UPDATED)
cs.CV updates on arXiv.org arxiv.org
Representing human performance at high-fidelity is an essential building
block in diverse applications, such as film production, computer games or
videoconferencing. To close the gap to production-level quality, we introduce
HumanRF, a 4D dynamic neural scene representation that captures full-body
appearance in motion from multi-view video input, and enables playback from
novel, unseen viewpoints. Our novel representation acts as a dynamic video
encoding that captures fine details at high compression rates by factorizing
space-time into a temporal matrix-vector decomposition. This …
applications arxiv building computer diverse dynamic fidelity fields film games gap human human performance humans neural radiance fields neural scene representation performance production quality representation video videoconferencing