A Projection-Based Surrogate Gradient Interpretation for Neural Codec Wrappers

• URL: http://arxiv.org/abs/2606.20671v1
• Date: Fri, 12 Jun 2026 11:29:17 GMT
• Title: A Projection-Based Surrogate Gradient Interpretation for Neural Codec Wrappers
• Abstract summary: We show that a surrogate gradient can be interpreted as a first-order local approximation of the video.<n>We show that it is effective not only for learning downscaling operations, but also for the more challenging task of full neural wrapping.
• Score: 9.436544348188598
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural wrappers are learned pre-and postprocessing networks designed to enhance the performance of conventional video codecs. Although these approaches can significantly improve compression efficiency, training them remains challenging due to the non-differentiability of video codecs, which arises from the multiple discrete decisions involved in the encoding process. Surrogate gradients have recently emerged as an effective solution for enabling end-to-end learning with conventional codecs. They offer two main advantages: they avoid training an additional network to mimic the codec, and they can improve compression performance. In particular, the recently proposed SCALED method, which leverages the true compression error, has shown strong results for training neural pre-processors such as downscalers. However, this SCALED gradient was originally introduced as a reparameterization trick, which limits its interpretability. In this paper, we show that this surrogate gradient can be interpreted as a first-order local approximation of the video codec, providing insight into its effectiveness. We further demonstrate that it is effective not only for learning downscaling operations, but also for the more challenging task of full neural wrapping with pre-and post-processing networks. Finally, we show that the approach generalizes well across different video codecs, quality factors, and tasks, including multiple downscaling ratios, yielding BD-Rate (PSNR) reductions of up to -23.59% on x264 and -20.07% on VVenC relative to standard resampling baselines.

Related papers

• High-Fidelity Video Compression based on Invertible Neural Transform and Implicit Conditioning [9.466904732249127]
  InnVC is an Invertible neural network based Video Codec for wide-range and high-fidelity compression.<n>To the best of our knowledge, InnVC is the first neural video covers operating poins from low fidelity to high fidelity within a single architecture scale.
  arXiv  Detail & Related papers  (2026-06-11T22:37:11Z)
• SCALED : Surrogate-gradient for Codec-Aware Learning of Downsampling in ABR Streaming [9.436544348188598]
  Over-the-Top (OTT) delivery now predominantly relies on Adaptive Bitrate (ABR) streaming.<n>Deep learning has spurred interest in jointly optimizing the ABR pipeline using learned resampling methods.<n>We introduce a novel framework that enables end-to-end training with real, non-differentiable codecs.
  arXiv  Detail & Related papers  (2026-01-30T10:38:35Z)
• Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding [56.066799081747845]
  The ever-growing size of neural networks poses serious challenges on resource-constrained devices.<n>We propose a novel post-training compression framework that combines rate-aware quantization with entropy coding.<n>Our method allows for very fast decoding and is compatible with arbitrary quantization grids.
  arXiv  Detail & Related papers  (2025-05-24T15:52:49Z)
• Exploiting Latent Properties to Optimize Neural Codecs [5.725546754007691]
  We propose to leverage the benefits of vector quantization and the entropy gradient to improve the performance of off-the-shelf codecs.<n>We show that these approaches save between 1 to 3% of the rate for the same quality across various pretrained methods.
  arXiv  Detail & Related papers  (2025-01-02T12:45:31Z)
• Compression-Realized Deep Structural Network for Video Quality Enhancement [78.13020206633524]
  This paper focuses on the task of quality enhancement for compressed videos. Most of the existing methods lack a structured design to optimally leverage the priors within compression codecs. A new paradigm is urgently needed for a more conscious'' process of quality enhancement.
  arXiv  Detail & Related papers  (2024-05-10T09:18:17Z)
• Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression [58.618625678054826]
  This study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.
  arXiv  Detail & Related papers  (2024-01-25T08:11:27Z)
• Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation [17.980800481385195]
  We present a novel model-agnostic pruning scheme based on gradient decay and adaptive layer-wise distillation. Results confirm that our method yields up to 65% reduction in MACs and 2x speed-up with less than 0.3dB drop in BD-PSNR.
  arXiv  Detail & Related papers  (2023-12-05T09:26:09Z)
• A Coding Framework and Benchmark towards Low-Bitrate Video Understanding [63.05385140193666]
  We propose a traditional-neural mixed coding framework that takes advantage of both traditional codecs and neural networks (NNs) The framework is optimized by ensuring that a transportation-efficient semantic representation of the video is preserved. We build a low-bitrate video understanding benchmark with three downstream tasks on eight datasets, demonstrating the notable superiority of our approach.
  arXiv  Detail & Related papers  (2022-02-06T16:29:15Z)
• Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder [73.48927855855219]
  We propose a system that learns to improve the encoding performance by enhancing its internal neural representations on both the encoder and decoder ends. Experiments demonstrate that our approach successfully improves the rate-distortion performance over JPEG across various quality metrics.
  arXiv  Detail & Related papers  (2022-01-27T20:20:03Z)
• Multitask Learning for VVC Quality Enhancement and Super-Resolution [11.446576112498596]
  We propose a learning-based solution as a post-processing step to enhance the decoded VVC video quality. Our method relies on multitask learning to perform both quality enhancement and super-resolution using a single shared network optimized for multiple levels.
  arXiv  Detail & Related papers  (2021-04-16T19:05:26Z)
• Content Adaptive and Error Propagation Aware Deep Video Compression [110.31693187153084]
  We propose a content adaptive and error propagation aware video compression system. Our method employs a joint training strategy by considering the compression performance of multiple consecutive frames instead of a single frame. Instead of using the hand-crafted coding modes in the traditional compression systems, we design an online encoder updating scheme in our system.
  arXiv  Detail & Related papers  (2020-03-25T09:04:24Z)

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.