Implicit Neural Representation for Hyperspectral Video Compression

Alfredo Scalera; Paul Murray; Jaime Zabalza

cs.CVSep 25, 2026

Implicit Neural Representation for Hyperspectral Video Compression

Authors: Alfredo Scalera, Paul Murray, Jaime Zabalza

Organizations: University of Strathclyde Department of Electronic & Electrical Engineering Glasgow, UK

Abstract

With the advent of snapshot cameras, hyperspectral video is becoming more readily available. In recent years, new applications have emerged which have led to increasingly larger datasets. However, hyperspectral video compression remains in the early stages. In this study, we explore the use of implicit neural representation as a candidate solution. We propose a novel extension of an existing RGB video compression model, achieving Bjøntegaard Delta PSNR gains of +4.99 dB and Bjøntegaard Delta rate of -88.88% compared to traditional hyperspectral image compression methods applied frame-by-frame. In addition to reconstruction quality, the effects on downstream task performance are measured in the form of object tracking success. Compared to video compressed with methods based on principal component analysis and JPEG2000 in low data regimes, our proposed method improves tracking area under the curve by up to 23.42% and distance precision by up to 35.56% on examples from the HOT2026 dataset.

Figures & tables

Fig. 1 : HS video compression with PCA+JPEG2000. The projection matrix $\boldsymbol{P}$ is quantized to $\hat{\boldsymbol{P}}$ before being written into the bitstream. Q represents min-max quantization and $\boldsymbol{s_{P}}=(\boldsymbol{P}_{\mathrm{min}},\boldsymbol{P}_{\mathrm{scale}})$ and analogously for $\boldsymbol{m}$ .

Fig. 2 : HS video compression with HNeRV-based method. (a) High-level frame reconstruction for overfitting. (b) Compression - decoder parameters $\theta_{\mathrm{dec}}$ are shared across all video frames while each frame has a unique set of latent variables $\boldsymbol{L}$ . Huffman coding losslessly compresses quantized latents $\boldsymbol{\hat{L}}$ and decoder parameters $\hat{\theta}_{\mathrm{dec}}$ .

Fig. 3 : INR-based compression affords higher fidelity. HS-HNeRV surpasses PCA+JPEG2000 in both spatial (left) and spectral (right) reconstruction at similar compression levels.

Compression Method	bpp	AUC	DP
Raw Sequence	–	$43.59$	$67.84$
PCA+JPEG2000	0.135	$24.55$	$42.80$
	0.275	$27.87$	$46.44$
	0.604	$37.92$	$69.92$
HS-HNeRV	0.133	$30.30$	$58.02$
	0.276	$33.37$	$61.24$

Table 1: CSSTrack performance on compressed HOT2026.

Fig. 4 : Generally, for equivalent PSNR values, HSFusion forces better spectral fidelity within each pixel (SAM metric). Each datum represents a hyperparameter search trial.

Fig. 5 : Qualitative comparison of reconstruction capabilities. Channel 16 of first frame from high_truck sequence. HS-HNeRV achieves a higher spatial and spectral quality.

Explore similar work

TeCoNeRV: Leveraging Temporal Coherence for Compressible Neural Representations for Videos
Feb 18, 2026Namitha Padmanabhan, Matthew Gwilliam, Abhinav ShrivastavaNeural Video Compression Implicit Neural Representations
Department of Computer Science, University of Maryland, College Park, USA.
Video Compression with Graph-inspired Neural Representation
Sep 2, 2026Changqi Wang, Ge Gao, Fan Zhang +4Neural Video Compression Implicit Neural Representations
University of Bristol · Bytedance Inc., San Diego, USA
tcnerv:dual-domain temporal context modeling for implicit neural video compression
Sep 15, 2026Xuezhi Xiang, Yixin Zhao, Heqi Xiang +2Implicit Neural Representations Neural Video Compression
Information and Communication Engineering, Harbin Engineering University, Harbin, 150001, China · Department of Computer Science, University of Toronto, Toronto, ON M5S 2E4, Canada · The Department of Computer Science, Kanagawa University, Kanagawa, 221-8686, Japan

Feb 18, 2026J/K move · Enter open · S save

TeCoNeRV: Leveraging Temporal Coherence for Compressible Neural Representations for Videos

Namitha Padmanabhan, Matthew Gwilliam, Abhinav Shrivastava

Department of Computer Science, University of Maryland, College Park, USA.

Neural Video Compression Implicit Neural Representations Hypernetworks

Open paper AskPDF arXiv

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/ .

Abstract

Explore similar work

TeCoNeRV: Leveraging Temporal Coherence for Compressible Neural Representations for Videos

Video Compression with Graph-inspired Neural Representation

tcnerv:dual-domain temporal context modeling for implicit neural video compression