TinyNeRV: Compact Neural Video Representations via Capacity Scaling, Distillation, and Low-Precision Inference

• URL: http://arxiv.org/abs/2604.09220v1
• Date: Fri, 10 Apr 2026 11:26:09 GMT
• Title: TinyNeRV: Compact Neural Video Representations via Capacity Scaling, Distillation, and Low-Precision Inference
• Abstract summary: Implicit neural video representations encode entire video sequences within the parameters of a neural network.<n>Recent work on Neural Representations for Videos (NeRV) has demonstrated competitive reconstruction performance.<n>This paper presents a systematic study of tiny NeRV architectures designed for efficient deployment.
• Score: 2.294014185517203
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Implicit neural video representations encode entire video sequences within the parameters of a neural network and enable constant time frame reconstruction. Recent work on Neural Representations for Videos (NeRV) has demonstrated competitive reconstruction performance while avoiding the sequential decoding process of conventional video codecs. However, most existing studies focus on moderate or high capacity models, leaving the behavior of extremely compact configurations required for constrained environments insufficiently explored. This paper presents a systematic study of tiny NeRV architectures designed for efficient deployment. Two lightweight configurations, NeRV-T and NeRV-T+, are introduced and evaluated across multiple video datasets in order to analyze how aggressive capacity reduction affects reconstruction quality, computational complexity, and decoding throughput. Beyond architectural scaling, the work investigates strategies for improving the performance of compact models without increasing inference cost. Knowledge distillation with frequency-aware focal supervision is explored to enhance reconstruction fidelity in low-capacity networks. In addition, the impact of lowprecision inference is examined through both post training quantization and quantization aware training to study the robustness of tiny models under reduced numerical precision. Experimental results demonstrate that carefully designed tiny NeRV variants can achieve favorable quality efficiency trade offs while substantially reducing parameter count, computational cost, and memory requirements. These findings provide insight into the practical limits of compact neural video representations and offer guidance for deploying NeRV style models in resource constrained and real-time environments. The official implementation is available at https: //github.com/HannanAkhtar/TinyNeRV-Implementation.

Related papers

• Binarized High-Efficiency RAW Video Restoration and Beyond [35.19326380579849]
  BinRVR is a binarized RAW video restoration framework that reduces parameters by approximately 96% while incurring only about 4% performance degradation.<n>We present a Binarized Information Interaction Module (BIIM) to jointly model spatial and temporal information in an efficient and unified manner.<n>We further explore the potential of our method on downstream video applications, including object detection and monocular depth estimation.
  arXiv  Detail & Related papers  (2026-08-17T16:03:50Z)
• LRConv-NeRV: Low Rank Convolution for Efficient Neural Video Compression [2.7920304852537527]
  This paper proposes LRConv-NeRV, an efficient NeRV variant that replaces selected dense 3x3 convolutional layers with structured low-rank separable convolutions.<n>Experiments demonstrate that applying LRConv only to the final decoder stage reduces decoder complexity by 68%.<n>Results establish LRConv-NeRV as a potential architectural alternative for efficient neural video decoding under low-precision and resource-constrained settings.
  arXiv  Detail & Related papers  (2026-03-18T20:31:59Z)
• Enhancing Neural Video Compression of Static Scenes with Positive-Incentive Noise [51.028614105626154]
  Static scene videos, such as surveillance feeds and videotelephony streams, constitute a dominant share of storage consumption and network traffic.<n>Traditional standardized codecs and neural video compression (NVC) methods struggle to encode these videos efficiently due to inadequate usage of temporal redundancy and severe distribution gaps between training and test data.<n>We propose to incorporate positive-incentive noise into NVC for static scene videos, where short-term temporal changes are reinterpreted as positive-incentive noise to facilitate model finetuning.
  arXiv  Detail & Related papers  (2026-03-06T09:47:25Z)
• NIRVANA: Structured pruning reimagined for large language models compression [50.651730342011014]
  We introduce NIRVANA, a novel pruning method designed to balance immediate zero-shot preservation accuracy with robust fine-tuning.<n>To further address the unique challenges posed by structured pruning, NIRVANA incorporates an adaptive sparsity allocation mechanism across layers and modules.<n>Experiments conducted on Llama3, Qwen, T5 models demonstrate that NIRVANA outperforms existing structured pruning methods under equivalent sparsity constraints.
  arXiv  Detail & Related papers  (2025-09-17T17:59:00Z)
• SR-NeRV: Improving Embedding Efficiency of Neural Video Representation via Super-Resolution [0.0]
  Implicit Neural Representations (INRs) have garnered significant attention for their ability to model complex signals in various domains.<n>We propose an INR-based video representation framework that integrates a general-purpose super-resolution (SR) network.<n>By offloading the reconstruction of fine details to a dedicated SR network pre-trained on natural images, the proposed method improves visual fidelity.
  arXiv  Detail & Related papers  (2025-04-30T03:31:40Z)
• SING: Semantic Image Communications using Null-Space and INN-Guided Diffusion Models [52.40011613324083]
  Joint source-channel coding systems (DeepJSCC) have recently demonstrated remarkable performance in wireless image transmission.<n>Existing methods focus on minimizing distortion between the transmitted image and the reconstructed version at the receiver, often overlooking perceptual quality.<n>We propose SING, a novel framework that formulates the recovery of high-quality images from corrupted reconstructions as an inverse problem.
  arXiv  Detail & Related papers  (2025-03-16T12:32:11Z)
• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• VQ-NeRV: A Vector Quantized Neural Representation for Videos [3.6662666629446043]
  Implicit neural representations (INR) excel in encoding videos within neural networks, showcasing promise in computer vision tasks like video compression and denoising. We introduce an advanced U-shaped architecture, Vector Quantized-NeRV (VQ-NeRV), which integrates a novel component--the VQ-NeRV Block. This block incorporates a codebook mechanism to discretize the network's shallow residual features and inter-frame residual information effectively.
  arXiv  Detail & Related papers  (2024-03-19T03:19:07Z)
• NERV++: An Enhanced Implicit Neural Video Representation [11.25130799452367]
  We introduce neural representations for videos NeRV++, an enhanced implicit neural video representation. NeRV++ is more straightforward yet effective enhancement over the original NeRV decoder architecture. We evaluate our method on UVG, MCL JVC, and Bunny datasets, achieving competitive results for video compression with INRs.
  arXiv  Detail & Related papers  (2024-02-28T13:00:32Z)
• Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective [64.04617968947697]
  We introduce a novel data-model co-design perspective: to promote superior weight sparsity. Specifically, customized Visual Prompts are mounted to upgrade neural Network sparsification in our proposed VPNs framework.
  arXiv  Detail & Related papers  (2023-12-03T13:50:24Z)
• CNeRV: Content-adaptive Neural Representation for Visual Data [54.99373641890767]
  We propose Neural Visual Representation with Content-adaptive Embedding (CNeRV), which combines the generalizability of autoencoders with the simplicity and compactness of implicit representation. We match the performance of NeRV, a state-of-the-art implicit neural representation, on the reconstruction task for frames seen during training while far surpassing for frames that are skipped during training (unseen images) With the same latent code length and similar model size, CNeRV outperforms autoencoders on reconstruction of both seen and unseen images.
  arXiv  Detail & Related papers  (2022-11-18T18:35:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.