TeCoNeRV: Leveraging Temporal Coherence for Compressible Neural Representations for Videos
2026-02-18 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method called TeCoNeRV to improve video compression using Implicit Neural Representations (INRs). Unlike previous methods that struggled with high-resolution videos due to memory and size issues, their approach breaks videos into smaller parts, stores only changes between segments, and encourages smooth changes over time. This results in better video quality, smaller file sizes, and faster encoding speeds compared to earlier models. Their method works efficiently at higher resolutions and on multiple datasets, showing practical improvements in video compression.
Implicit Neural RepresentationsVideo CompressionHypernetworkWeight PredictionPatch TubeletsBitstreamTemporal CoherencePSNREncoding SpeedResidual Storage
Authors
Namitha Padmanabhan, Matthew Gwilliam, Abhinav Shrivastava
Abstract
Implicit Neural Representations (INRs) have recently demonstrated impressive performance for video compression. However, since a separate INR must be overfit for each video, scaling to high-resolution videos while maintaining encoding efficiency remains a significant challenge. Hypernetwork-based approaches predict INR weights (hyponetworks) for unseen videos at high speeds, but with low quality, large compressed size, and prohibitive memory needs at higher resolutions. We address these fundamental limitations through three key contributions: (1) an approach that decomposes the weight prediction task spatially and temporally, by breaking short video segments into patch tubelets, to reduce the pretraining memory overhead by 20$\times$; (2) a residual-based storage scheme that captures only differences between consecutive segment representations, significantly reducing bitstream size; and (3) a temporal coherence regularization framework that encourages changes in the weight space to be correlated with video content. Our proposed method, TeCoNeRV, achieves substantial improvements of 2.47dB and 5.35dB PSNR over the baseline at 480p and 720p on UVG, with 36% lower bitrates and 1.5-3$\times$ faster encoding speeds. With our low memory usage, we are the first hypernetwork approach to demonstrate results at 480p, 720p and 1080p on UVG, HEVC and MCL-JCV. Our project page is available at https://namithap10.github.io/teconerv/ .