Gen2-VC is proposed, a generative video compression framework that enhances the outputs of learned and conventional codecs with a pretrained video prior, leaving their bitstreams and reference update processes unchanged.
Abstract
Under stringent bitrate constraints, existing video codecs struggle to balance source fidelity and perceptual realism. Distortion-oriented codecs often oversmooth details, while generative codecs risk introducing content and structural deviations and rely on codec-specific designs. This motivates a question: Can existing codecs achieve a better distortion--perception trade-off through simple, reusable adaptation? Our insight is that native codec reconstructions provide a shared interface through which generative refinement is anchored to source content while remaining decoupled from codec-specific representations. We therefore propose Gen2-VC, a generative video compression framework that enhances the outputs of learned and conventional codecs with a pretrained video prior, leaving their bitstreams and reference update processes unchanged. With the codec, VAE, and generative backbone frozen, lightweight LoRA adapters refine codec reconstruction through single-frame spatial adaptation followed by multi-frame temporal adaptation with the video prior. Using Wan2.1-T2V-1.3B, Gen2-VC-DCVC-UF outperforms previous leading codecs in LPIPS/DISTS and, to our knowledge, is the first generative video codec to surpass VTM-23.0 in both PSNR and MS-SSIM at low bitrates, based on BD-rates averaged over six datasets. Compared to VTM-23.0, it reduces bitrate by an average of 86.65% and 94.24% at matched LPIPS and DISTS, respectively. Adapters trained only on DCVC-UF improve perceptual quality on DCVC-RT, ECM, VTM, and HM without retraining.
Presley is presented, which extends the prior conference work ELVIS by replacing destructive block removal with adaptive in-place degradation under a removability mask, signaling per-block strength in a bit-packed side channel, and restoring via generative backbones conditioned on transmitted visual priors rather than...
Emanuele Artioli, F. Tashtarian, C. Timmerer· 0 citations
Generative image compression produces visually plausible reconstructions at low bitrates, yet their behavior as the rate approaches zero remains largely unexplored. When pushed below normal operating rates, representative codecs undergo semantic collapse: rather than gracefully losing source-specific detail, they produ...
Tian-Yu Zhang, Zhao-Yang Jia, Hou-Qiang Li et al.· 0 citations
P4VC is introduced, a Positive Perturbation based Perceptual Preprocessing framework that generates adaptive perturbations before compression to enhance the rate-perception trade-off and step beyond conventional frameworks and focus on preprocessing ahead of compression.
Mai Xu, Yi-Chen Guo, Shang-Mou Zhang et al.· IEEE Transactions on Pattern...· 0 citations
FLM is a frequency-aware language model that improves compression efficiency through frequency-domain probabilistic modeling while retaining deterministic reconstruction and is validated to be applicable to the lossless recompression task with competitive performance.
Jia-Run Chen, Ke-Jun Wu, Li Li et al.· 0 citations
COLD is presented, the first learned video watermark built around codec compression as its design target, which survives that compression by embedding the payload in the latent space of a frozen generative video autoencoder and recovering it by re-encoding the received video into that same latent space.
A context-aware framework that specializes a pretrained semantic decoder to each group of pictures by optimizing only its channel-wise scale factors and transposed-convolution biases, enabling the receiver to reproduce the adapted decoder without full-model retraining is introduced.
P. Samarathunga, Yasith Ganearachchi, Thanuj Fernando et al.· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.