CATRF: Codec-Adaptive TriPlane Radiance Fields for Volumetric Content Delivery

TL;DR

CATRF introduces a novel framework that integrates standard video codecs into volumetric radiance field compression, enabling efficient, low-bitrate free-viewpoint video streaming without learned codecs.

Contribution

It presents a codec-in-the-loop training method for radiance fields that adapts features to standard codecs, improving compression and decoding speed.

Findings

Outperforms codec-agnostic and learned-codec baselines in rate-distortion trade-off.

Achieves better compression efficiency and decoding speed than recent methods.

Demonstrates practical volumetric content delivery at low bitrates.

Abstract

Volumetric media promises next-generation content delivery applications, but its bandwidth demand remains a key bottleneck. Implicit and hybrid volumetric representations reduce model sizes, yet still require careful coding to reach 2D video-like bitrates. We present CATRF, a standard-codec-in-the-loop compression framework for plane-factorized radiance fields. During training, we quantize and pack 2D feature planes into codec-friendly canvases, run a standard codec roundtrip (JPEG/VP9/HEVC/AV1), then unpack and dequantize the decoded features before volume rendering. We use a straight-through estimator (STE) to insert the non-differentiable, standard codec pipeline into the training loop, allowing radiance-field features to adapt directly to the real, client-side codec distortions without introducing any learned codec parameters. On both static and dynamic benchmarks, CATRF consistently achieves a better rate-distortion trade-off over codec-agnostic and learned-codec-in-the-loop baselines, and also outperforms recent compressed 3DGS methods in both compression efficiency and decoding speed. These results highlight a practical path toward low-bitrate, compression-resilient volumetric representations for free-viewpoint video streaming.