SIEDD: Shared-Implicit Encoder with Discrete Decoders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rangarajan, Vikram, Maiya, Shishira, Ehrlich, Max, Shrivastava, Abhinav
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918075211710464
author Rangarajan, Vikram
Maiya, Shishira
Ehrlich, Max
Shrivastava, Abhinav
author_facet Rangarajan, Vikram
Maiya, Shishira
Ehrlich, Max
Shrivastava, Abhinav
contents Implicit Neural Representations (INRs) offer exceptional fidelity for video compression by learning per-video optimized functions, but their adoption is crippled by impractically slow encoding times. Existing attempts to accelerate INR encoding often sacrifice reconstruction quality or crucial coordinate-level control essential for adaptive streaming and transcoding. We introduce SIEDD (Shared-Implicit Encoder with Discrete Decoders), a novel architecture that fundamentally accelerates INR encoding without these compromises. SIEDD first rapidly trains a shared, coordinate-based encoder on sparse anchor frames to efficiently capture global, low-frequency video features. This encoder is then frozen, enabling massively parallel training of lightweight, discrete decoders for individual frame groups, further expedited by aggressive coordinate-space sampling. This synergistic design delivers a remarkable 20-30X encoding speed-up over state-of-the-art INR codecs on HD and 4K benchmarks, while maintaining competitive reconstruction quality and compression ratios. Critically, SIEDD retains full coordinate-based control, enabling continuous resolution decoding and eliminating costly transcoding. Our approach significantly advances the practicality of high-fidelity neural video compression, demonstrating a scalable and efficient path towards real-world deployment. Our codebase is available at https://github.com/VikramRangarajan/SIEDD .
format Preprint
id arxiv_https___arxiv_org_abs_2506_23382
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SIEDD: Shared-Implicit Encoder with Discrete Decoders
Rangarajan, Vikram
Maiya, Shishira
Ehrlich, Max
Shrivastava, Abhinav
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Implicit Neural Representations (INRs) offer exceptional fidelity for video compression by learning per-video optimized functions, but their adoption is crippled by impractically slow encoding times. Existing attempts to accelerate INR encoding often sacrifice reconstruction quality or crucial coordinate-level control essential for adaptive streaming and transcoding. We introduce SIEDD (Shared-Implicit Encoder with Discrete Decoders), a novel architecture that fundamentally accelerates INR encoding without these compromises. SIEDD first rapidly trains a shared, coordinate-based encoder on sparse anchor frames to efficiently capture global, low-frequency video features. This encoder is then frozen, enabling massively parallel training of lightweight, discrete decoders for individual frame groups, further expedited by aggressive coordinate-space sampling. This synergistic design delivers a remarkable 20-30X encoding speed-up over state-of-the-art INR codecs on HD and 4K benchmarks, while maintaining competitive reconstruction quality and compression ratios. Critically, SIEDD retains full coordinate-based control, enabling continuous resolution decoding and eliminating costly transcoding. Our approach significantly advances the practicality of high-fidelity neural video compression, demonstrating a scalable and efficient path towards real-world deployment. Our codebase is available at https://github.com/VikramRangarajan/SIEDD .
title SIEDD: Shared-Implicit Encoder with Discrete Decoders
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.23382