CATRF: Codec-Adaptive TriPlane Radiance Fields for Volumetric Content Delivery
Researchers have developed CATRF, a novel framework for compressing volumetric media to improve content delivery. This method integrates standard codecs like JPEG and AV1 directly into the training loop, allowing feature planes to adapt to codec-specific distortions. By using a straight-through estimator, CATRF achieves a superior rate-distortion trade-off compared to existing methods, enabling more efficient and faster decoding for free-viewpoint video streaming. AI
IMPACT Enables more efficient streaming of volumetric content by adapting compression to codec distortions.