pith. sign in

arxiv: 2606.28163 · v1 · pith:UPKF2UB2new · submitted 2026-06-26 · 📡 eess.IV · cs.CV

Enhanced Neural Video Representation Compression across Extreme Complexity and Quality Scales

Ho Man Kwan , Tianhao Peng , Fan Zhang , Mike Nilsson , Andrew Gower , David Bull This is my paper

Pith reviewed 2026-06-29 02:11 UTC · model grok-4.3

classification 📡 eess.IV cs.CV
keywords neural video compressionimplicit neural representationsINR-based codeccomplexity scalabilityfeature gridsentropy modelreal-time decoding
0
0 comments X

The pith

NVRC++ maintains four fixed complexity levels while spanning wide bitrates and qualities in INR-based video compression.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces NVRC++ to solve the problem that existing INR video codecs either lose compression performance when kept lightweight or increase model complexity as quality demands rise. It does this with a lightweight INR that uses multiple high-resolution feature grids, an optimization framework that overfits those grids efficiently on long sequences, and an advanced entropy model to compress the resulting parameters. The result is four complexity tiers ranging from 7k to 360k MACs per pixel, each covering broad bitrate and quality ranges while supporting real-time decoding. Experiments show it matches the rate-distortion performance of the prior state-of-the-art INR codec NVRC but decodes up to 7.6 times faster.

Core claim

NVRC++ is a novel INR-based video codec that utilizes a lightweight INR with multiple high-resolution feature grids, paired with an optimization framework for efficient overfitting on long video sequences and an advanced entropy model for compressing the grid parameters, thereby providing four complexity levels from 7kMACs/pixel to 360kMACs/pixel, each spanning wide bitrate and quality ranges while supporting real-time decoding and delivering up to 7.6x faster decoding than NVRC at comparable performance.

What carries the argument

Lightweight INR with multiple high-resolution feature grids, which maintains fixed complexity while enabling wide bitrate-quality coverage through spatio-temporal redundancy exploitation.

If this is right

  • Each of the four complexity levels can be deployed independently for different hardware constraints while still covering broad quality ranges.
  • The same architecture supports real-time decoding without needing to increase model size as bitrate or quality targets rise.
  • Spatio-temporal redundancies are exploited directly in the grid parameters rather than through added model capacity.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The grid-plus-entropy design may transfer to other high-dimensional signals such as volumetric video or light-field data.
  • Hardware-specific quantization of the feature grids could further reduce the memory footprint beyond the reported entropy coding gains.
  • The fixed-complexity property suggests the method could be combined with adaptive streaming systems that switch levels without retraining.

Load-bearing premise

The optimization framework can overfit high-resolution grids for long sequences without prohibitive compute or memory costs, and the entropy model can efficiently compress the high-dimensional parameters.

What would settle it

Run the reported experiments on a new set of long high-resolution videos and measure whether any complexity level exceeds its stated MACs/pixel budget or fails to reach real-time decoding speed.

Figures

Figures reproduced from arXiv: 2606.28163 by Andrew Gower, David Bull, Fan Zhang, Ho Man Kwan, Mike Nilsson, Tianhao Peng.

Figure 1
Figure 1. Figure 1: The trade off between decoding complexity (in terms of FPS and MACs/pixel) and coding performance (in BD-rate against x265 (veryslow)) of the proposed method and existing neural video codecs. For INR-based approaches, the entropy decoding steps are excluded in the FPS calculation as they are separated process with the frame decoding and not optimized. NVRC++ achieves a superior complexity-compression trade… view at source ↗
Figure 2
Figure 2. Figure 2: The overall NVRC++ framework. It contains a hierarchical parameter coding structure, while also contains an advance grid entropy model based on temporal, spatial and scale priors, and the improved INR network, HiNeRV++. It also features random sampling for updating only partial parameters for more efficient training process. the model complexity scales with the target bitrate/quality, which is a critical p… view at source ↗
Figure 3
Figure 3. Figure 3: (Left) Proposed in-parameter coding and multi-reference inputs. Grid parame￾ters are organized into temporal slices and compressed using a Hierarchical-B structure to leverage inter-slice dependencies. Unlike standard practices that rely solely on inter￾polated features, HiNeRV++ utilizes neighboring raw slices as multi-reference context to enhance reconstruction. While K = 3/4 is shown for illustration, o… view at source ↗
Figure 4
Figure 4. Figure 4: (Left) RD curves of benchmarked codecs. (Right) Comparison of NVRC++ (92.5kMACs/px) with NVRC (with fixed complexity (102.7kMACs/px)) for scalability. Finally, the ultra-lightweight S1 comfortably outperforms x265 and recent INRs like C3 at similar complexities, while rivaling HiNeRV and HM in MS-SSIM. Decoding speed and complexity. A key advantage of NVRC++ is its con￾stant decoding complexity across bitr… view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative comparison between GT, NVRC, DCVC-RT and NVRC++ (ours). 5.3 Additional analysis HiNeRV++ vs HiNeRV. We have also validated the proposed HiNeRV++ architecture by comparing it with the original HiNeRV, with results shown in Tab. 3. It is noted that by offloading the representational burden from neural layers to high-resolution feature grids, HiNeRV++ drastically increases grid parameters while re… view at source ↗
read the original abstract

Implicit neural representations (INRs) have recently emerged as a promising approach to video compression, delivering competitive rate-distortion performance alongside rapid decoding. However, existing neural video codecs struggle to balance complexity and scalability. Lightweight models often suffer from degraded compression performance when scaled to different bitrate/quality levels, whereas high-performance models exhibit limited scalability, as their model complexity typically increases with quality. This lack of a unified architecture capable of maintaining consistent complexity across a wide range of bitrates severely limits their diverse real-world deployment. To address these challenges, we introduce NVRC++, a novel INR-based video codec that utilizes a lightweight INR with multiple high-resolution feature grids, providing high scalability at any given complexity level. This is paired with an optimization framework that enables efficient overfitting on high-resolution grids for long video sequences, thereby exploiting spatio-temporal redundancies without prohibitive computational or memory overhead. Additionally, an advanced entropy model is designed for efficiently compressing the high-dimensional grid parameters. As a result, NVRC++ provides four complexity levels (from 7kMACs/pixel to 360kMACs/pixel), each spanning wide bitrate and quality ranges while supporting real-time decoding. The experimental results show that NVRC++ offers a much faster decoding speed (up to 7.6x) compared to the SOTA INR-based video codec, NVRC, while delivering comparable performance.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript introduces NVRC++, an INR-based video codec using a lightweight INR with multiple high-resolution feature grids, paired with an optimization framework for efficient overfitting on long sequences and an advanced entropy model for grid parameters. It claims four fixed complexity levels (7k–360k MACs/pixel) each spanning wide bitrate/quality ranges with real-time decoding, delivering up to 7.6× faster decoding than NVRC at comparable performance.

Significance. If the results hold, this addresses a key limitation in INR video codecs by enabling consistent complexity across quality scales, which supports diverse real-world deployment. The fixed-complexity operating points and real-time capability are practical strengths; the optimization and entropy components are presented as jointly enabling scalability without prohibitive overhead.

major comments (2)
  1. [Experimental Results] Experimental Results section: the central claims of 7.6× decoding speedup and comparable rate-distortion performance to NVRC are load-bearing but rest on unspecified datasets, sequence counts, hardware platforms, and statistical reporting; without these, it is impossible to assess whether post-hoc choices or limited test conditions affect the cross-method comparison.
  2. [Method] Method section (optimization framework description): the claim that the framework enables efficient overfitting on high-resolution grids for long sequences without prohibitive overhead lacks quantitative analysis (e.g., memory scaling curves or per-sequence runtime breakdowns) that would confirm it supports the four complexity levels at the stated ranges.
minor comments (2)
  1. The abstract would be clearer if it named the specific video datasets and resolution ranges used for the reported results.
  2. Notation for MACs/pixel and the four complexity levels should be defined at first use with a table reference for reproducibility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major comment below and indicate the revisions that will be made to improve clarity and support for the claims.

read point-by-point responses

  1. Referee: [Experimental Results] Experimental Results section: the central claims of 7.6× decoding speedup and comparable rate-distortion performance to NVRC are load-bearing but rest on unspecified datasets, sequence counts, hardware platforms, and statistical reporting; without these, it is impossible to assess whether post-hoc choices or limited test conditions affect the cross-method comparison.

    Authors: We agree that greater explicitness is needed to allow readers to evaluate the comparisons. The manuscript references standard video compression benchmarks, but the Experimental Results section will be revised to add a dedicated paragraph specifying the datasets, exact sequence counts, hardware platforms used for timing, and statistical reporting (means and variability across sequences). This will be placed at the start of the section to support assessment of the 7.6× speedup and rate-distortion results. revision: yes

  2. Referee: [Method] Method section (optimization framework description): the claim that the framework enables efficient overfitting on high-resolution grids for long sequences without prohibitive overhead lacks quantitative analysis (e.g., memory scaling curves or per-sequence runtime breakdowns) that would confirm it supports the four complexity levels at the stated ranges.

    Authors: We concur that quantitative support would strengthen the description. The revised Method section will incorporate new analysis consisting of memory scaling curves versus sequence length and grid resolution, together with per-sequence runtime breakdowns for the overfitting stage across the four complexity levels. These will be presented in additional figures and text to demonstrate support for the claimed operating points. revision: yes

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The paper presents NVRC++ as an empirical engineering contribution: a lightweight INR architecture augmented with multiple high-resolution grids, paired with a described optimization framework and entropy model. These components are introduced as design choices that enable the reported scalability across complexity levels and real-time decoding. Performance claims rest on experimental benchmarking against the external SOTA method NVRC rather than any internal derivation, equation, or fitted parameter that reduces to the inputs by construction. No self-definitional loops, uniqueness theorems, or ansatzes smuggled via self-citation appear in the load-bearing steps. The derivation chain is therefore self-contained as a set of proposed techniques validated by results.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review reveals no explicit free parameters, axioms, or invented entities. The central claims rest on unstated assumptions about the effectiveness of the optimization and entropy components.

pith-pipeline@v0.9.1-grok · 5784 in / 1139 out tokens · 26891 ms · 2026-06-29T02:11:04.941357+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

56 extracted references · 8 canonical work pages · 1 internal anchor

  1. [1]

    In: ICLR

    Ballé, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. In: ICLR. OpenReview.net (2017)

    2017

  2. [2]

    In: ICLR

    Ballé, J., Minnen, D., Singh, S., Hwang, S.J., Johnston, N.: Variational image compression with a scale hyperprior. In: ICLR. OpenReview.net (2018)

    2018

  3. [3]

    ITU SG16 Doc

    Bjontegaard, G.: Calculation of average psnr differences between rd-curves. ITU SG16 Doc. VCEG-M33 (2001)

    2001

  4. [4]

    Bross, B., Wang, Y.K., Ye, Y., Liu, S., Chen, J., Sullivan, G.J., Ohm, J.R.: Overview oftheversatilevideocoding(VVC)standardanditsapplications.IEEETransactions on Circuits and Systems for Video Technology31(10), 3736–3764 (2021)

    2021

  5. [5]

    In: the JVET meeting

    Browne, A., Ye, Y., Kim, S.H.: Algorithm description for Versatile Video Coding and Test Model 19 (VTM 19). In: the JVET meeting. ITU-T and ISO/IEC (2023)

    2023

  6. [6]

    Academic Press (2021)

    Bull, D., Zhang, F.: Intelligent image and video compression: communicating pictures. Academic Press (2021)

    2021

  7. [7]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Chen, H., Gwilliam, M., Lim, S.N., Shrivastava, A.: HNeRV: A hybrid neural repre- sentation for videos. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 10270–10279 (2023)

    2023

  8. [8]

    Advances in Neural Information Processing Systems34, 21557–21568 (2021)

    Chen, H., He, B., Wang, H., Ren, Y., Lim, S.N., Shrivastava, A.: NeRV: Neural representations for videos. Advances in Neural Information Processing Systems34, 21557–21568 (2021)

    2021

  9. [9]

    IEEE Trans

    Chen, Y., Xie, H., Chen, C., Gao, Z., Benjak, M., Peng, W., Ostermann, J.: Maskcrt: Masked conditional residual transformer for learned video compression. IEEE Trans. Circuits Syst. Video Technol.34(11), 11980–11992 (2024) 16 H. M. Kwan et al

    2024

  10. [10]

    In: Proceedings of the 31st ACM International Conference on Multimedia

    Chen, Z., Relic, L., Azevedo, R., Zhang, Y., Gross, M., Xu, D., Zhou, L., Schroers, C.: Neural video compression with spatio-temporal cross-covariance transformers. In: Proceedings of the 31st ACM International Conference on Multimedia. pp. 8543–8551 (2023)

    2023

  11. [11]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Gao, G., Kwan, H.M., Zhang, F., Bull, D.: Pnvc: Towards practical inr-based video compression. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 39, pp. 3068–3076 (2025)

    2025

  12. [12]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Gomes, C., Azevedo, R., Schroers, C.: Video compression with entropy-constrained neural representations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 18497–18506 (2023)

    2023

  13. [13]

    In: ICCV

    Habibian, A., van Rozendaal, T., Tomczak, J.M., Cohen, T.: Video compression with rate-distortion autoencoders. In: ICCV. pp. 7032–7041. IEEE (2019)

    2019

  14. [14]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    He, B., Yang, X., Wang, H., Wu, Z., Chen, H., Huang, S., Ren, Y., Lim, S.N., Shrivas- tava, A.: Towards scalable neural representation for diverse videos. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 6132–6142 (2023)

    2023

  15. [15]

    In: CVPR

    He, D., Zheng, Y., Sun, B., Wang, Y., Qin, H.: Checkerboard Context Model for Efficient Learned Image Compression. In: CVPR. pp. 14771–14780 (2021)

    2021

  16. [16]

    Improving neural networks by preventing co-adaptation of feature detectors

    Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)

    work page internal anchor Pith review Pith/arXiv arXiv 2012

  17. [17]

    In: European Conference on Computer Vision

    Ho, Y.H., Chang, C.P., Chen, P.Y., Gnutti, A., Peng, W.H.: CANF-VC: Conditional augmented normalizing flows for video compression. In: European Conference on Computer Vision. pp. 207–223. Springer (2022)

    2022

  18. [18]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Jia, Z., Li, B., Li, J., Xie, W., Qi, L., Li, H., Lu, Y.: Towards practical real-time neural video compression. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 12543–12552 (2025)

    2025

  19. [19]

    In: Proceedings of the 33rd ACM International Conference on Multimedia

    Jiang, W., Li, J., Zhang, K., Zhang, L.: Biecvc: Gated diversification of bidirec- tional contexts for learned video compression. In: Proceedings of the 33rd ACM International Conference on Multimedia. pp. 7248–7257 (2025)

    2025

  20. [20]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Jiang, W., Li, J., Zhang, K., Zhang, L.: Ecvc: Exploiting non-local correlations in multiple frames for contextual video compression. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 7331–7341 (2025)

    2025

  21. [21]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    Kim, H., Bauer, M., Theis, L., Schwarz, J.R., Dupont, E.: C3: High-performance and low-complexity neural compression from a single image or video. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    2024

  22. [22]

    Advances in Neural Information Processing Systems36(2024)

    Kwan, H.M., Gao, G., Zhang, F., Gower, A., Bull, D.: HiNeRV: Video compres- sion with hierarchical encoding-based neural representation. Advances in Neural Information Processing Systems36(2024)

    2024

  23. [23]

    arXiv preprint arXiv:2409.07414 (2024)

    Kwan, H.M., Gao, G., Zhang, F., Gower, A., Bull, D.: Nvrc: Neural video represen- tation compression. arXiv preprint arXiv:2409.07414 (2024)

    work page arXiv 2024

  24. [24]

    CoRRabs/2512.04019 (2025)

    Kwan, H.M., Peng, T., Gao, G., Zhang, F., Nilsson, M., Gower, A., Bull, D.: Ultra-lightweight neural video representation compression. CoRRabs/2512.04019 (2025)

    work page arXiv 2025

  25. [25]

    Kwan, H.M., Zhang, F., Gower, A., Bull, D.: Immersive video compression using implicit neural representations. In: PCS. pp. 1–5. IEEE (2024)

    2024

  26. [26]

    arXiv preprint arXiv:2104.07930 (2021) Enhanced Neural Video Representation Compression 17

    Ladune, T., Philippe, P., Hamidouche, W., Zhang, L., Déforges, O.: Conditional coding for flexible learned video compression. arXiv preprint arXiv:2104.07930 (2021) Enhanced Neural Video Representation Compression 17

    work page arXiv 2021

  27. [27]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Ladune, T., Philippe, P., Henry, F., Clare, G., Leguay, T.: COOL-CHIC: Coordinate- based low complexity hierarchical image codec. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 13515–13522 (2023)

    2023

  28. [28]

    In: Proceedings of the 31st ACM International Conference on Multimedia

    Lee, J.C., Rho, D., Ko, J.H., Park, E.: Ffnerv: Flow-guided frame-wise neural representations for videos. In: Proceedings of the 31st ACM International Conference on Multimedia. pp. 7859–7870 (2023)

    2023

  29. [29]

    In: 2024 Data Compression Conference (DCC)

    Leguay, T., Ladune, T., Philippe, P., Déforges, O.: COOL-CHIC video: Learned video coding with 800 parameters. In: 2024 Data Compression Conference (DCC). pp. 23–32. IEEE (2024)

    2024

  30. [30]

    In: NeurIPS

    Li, J., Li, B., Lu, Y.: Deep contextual video compression. In: NeurIPS. pp. 18114– 18125 (2021)

    2021

  31. [31]

    In: ACM Multimedia

    Li, J., Li, B., Lu, Y.: Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression. In: ACM Multimedia. pp. 1503–1511. ACM (2022)

    2022

  32. [32]

    In: CVPR

    Li, J., Li, B., Lu, Y.: Neural video compression with diverse contexts. In: CVPR. pp. 22616–22626. IEEE (2023)

    2023

  33. [33]

    In: Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Li, J., Li, B., Lu, Y.: Neural video compression with feature modulation. In: Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 26099–26108 (2024)

    2024

  34. [34]

    In: European Conference on Computer Vision

    Li, Z., Wang, M., Pi, H., Xu, K., Mei, J., Liu, Y.: E-nerv: Expedite neural video representation with disentangled spatial-temporal context. In: European Conference on Computer Vision. pp. 267–284. Springer (2022)

    2022

  35. [35]

    In: European Conference on Computer Vision

    Liu, J., Wang, S., Ma, W.C., Shah, M., Hu, R., Dhawan, P., Urtasun, R.: Condi- tional entropy coding for efficient video compression. In: European Conference on Computer Vision. pp. 453–468. Springer (2020)

    2020

  36. [36]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Lu, G., Ouyang, W., Xu, D., Zhang, X., Cai, C., Gao, Z.: DVC: An end-to-end deep video compression framework. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 11006–11015 (2019)

    2019

  37. [37]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Maiya, S.R., Girish, S., Ehrlich, M., Wang, H., Lee, K.S., Poirson, P., Wu, P., Wang, C., Shrivastava, A.: Nirvana: Neural implicit representations of videos with adaptive networks and autoregressive patch-wise modeling. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 14378–14387 (2023)

    2023

  38. [38]

    Vct: A video compression transformer.arXiv preprint arXiv:2206.07307, 2022

    Mentzer, F., Toderici, G., Minnen, D., Hwang, S.J., Caelles, S., Lucic, M., Agustsson, E.: VCT: A video compression transformer. arXiv preprint arXiv:2206.07307 (2022)

    work page arXiv 2022

  39. [39]

    In: MMSys

    Mercat, A., Viitanen, M., Vanne, J.: UVG Dataset: 50/120fps 4K Sequences for Video Codec Analysis and Development. In: MMSys. pp. 297–302. ACM (2020)

    2020

  40. [40]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: Learning 3d reconstruction in function space. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 4460–4470 (2019)

    2019

  41. [41]

    Commu- nications of the ACM65(1), 99–106 (2021)

    Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: Representing scenes as neural radiance fields for view synthesis. Commu- nications of the ACM65(1), 99–106 (2021)

    2021

  42. [42]

    In: NeurIPS

    Minnen, D., Ballé, J., Toderici, G.: Joint autoregressive and hierarchical priors for learned image compression. In: NeurIPS. pp. 10794–10803 (2018)

    2018

  43. [43]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: Deepsdf: Learning continuous signed distance functions for shape representation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 165–174 (2019)

    2019

  44. [44]

    In: the JVET meeting

    Rosewarne, C., Sharman, K., Sjoberg, R., Sullivan, G.: High efficiency video coding (HEVC) test model 16 (HM 16) improved encoder description update 16. In: the JVET meeting. ITU-T and ISO/IEC (2022) 18 H. M. Kwan et al

    2022

  45. [45]

    IEEE Transactions on Multimedia (2025)

    Sheng,X.,Li,L.,Liu,D.,Wang,S.:Bi-directionaldeepcontextualvideocompression. IEEE Transactions on Multimedia (2025)

    2025

  46. [46]

    In: CVPR

    Shi, W., Caballero, J., Huszar, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., Wang, Z.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: CVPR. pp. 1874–1883. IEEE Computer Society (2016)

    2016

  47. [47]

    Advances in neural information processing systems33, 7462–7473 (2020)

    Sitzmann, V., Martel, J., Bergman, A., Lindell, D., Wetzstein, G.: Implicit neural representations with periodic activation functions. Advances in neural information processing systems33, 7462–7473 (2020)

    2020

  48. [48]

    IEEE Transactions on circuits and systems for video technology22(12), 1649–1668 (2012)

    Sullivan, G.J., Ohm, J.R., Han, W.J., Wiegand, T.: Overview of the high efficiency video coding (HEVC) standard. IEEE Transactions on circuits and systems for video technology22(12), 1649–1668 (2012)

    2012

  49. [49]

    In: Proceedings of the IEEE conference on computer vision and pattern recognition

    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1–9 (2015)

    2015

  50. [50]

    In: VCIP

    Teng, S., Jiang, Y., Gao, G., Zhang, F., Davis, T., Liu, Z., Bull, D.: Benchmarking conventional and learned video codecs with a low-delay configuration. In: VCIP. pp. 1–5. IEEE (2024)

    2024

  51. [51]

    In: ICIP

    Wang, H., Gan, W., Hu, S., Lin, J.Y., Jin, L., Song, L., Wang, P., Katsavounidis, I., Aaron, A., Kuo, C.J.: MCL-JCV: A JND-based H.264/AVC video quality assessment dataset. In: ICIP. pp. 1509–1513. IEEE (2016)

    2016

  52. [52]

    x265:https://www.videolan.org/developers/x265.html

  53. [53]

    In: The Eleventh International Conference on Learning Repre- sentations (2022)

    Xiang, J., Tian, K., Zhang, J.: MIMT: Masked image modeling transformer for video compression. In: The Eleventh International Conference on Learning Repre- sentations (2022)

    2022

  54. [54]

    arXiv preprint arXiv:2402.18152 (2024)

    Zhang, X., Yang, R., He, D., Ge, X., Xu, T., Wang, Y., Qin, H., Zhang, J.: Boosting neural representations for videos with a conditional decoder. arXiv preprint arXiv:2402.18152 (2024)

    work page arXiv 2024

  55. [55]

    arXiv preprint arXiv:2112.11312 (2021)

    Zhang, Y., Van Rozendaal, T., Brehmer, J., Nagel, M., Cohen, T.: Implicit neural video compression. arXiv preprint arXiv:2112.11312 (2021)

    work page arXiv 2021

  56. [56]

    arXiv preprint arXiv:2506.15276 (2025)

    Zhu, J., Zhang, X., Tang, L., Jiang, J.: Msnerv: neural video representation with multi-scale feature fusion. arXiv preprint arXiv:2506.15276 (2025)

    work page arXiv 2025