Thread-Efficient Decoding for Neural Texture Compression

• URL: http://arxiv.org/abs/2608.27888v1
• Date: Fri, 28 Aug 2026 03:52:48 GMT
• Title: Thread-Efficient Decoding for Neural Texture Compression
• Abstract summary: NTC achieves higher compression ratios than BCn formats but suffers from thread divergence.<n>We propose a shared decoder architecture -- trained with a gradual decoder freezing schedule -- combined with texture clustering to reduce thread divergence by 25%-52%.<n>We evaluate our method on over 500 textures and multiple real rendering scenes, demonstrating up to 8.48x speedup on the Radeon RX 9070 XT GPU.
• Score: 0.77451677278277
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural texture compression (NTC) achieves higher compression ratios than BCn formats but suffers from GPU thread divergence, which significantly reduces runtime performance. In this work, we propose a shared decoder MLP architecture -- trained with a gradual decoder freezing schedule -- combined with texture clustering to reduce thread divergence by 25%-52% while preserving rendering quality. We evaluate our method on over 500 textures and multiple real rendering scenes, demonstrating up to 8.48x speedup on the Radeon RX 9070 XT GPU compared to non-shared baselines. Our key contributions include: (1) a unified shared decoder architecture that reduces divergence by grouping textures; (2) a training recipe with gradual decoder freezing that improves stability and reconstruction accuracy; (3) a semantic clustering strategy using CLIP embeddings that groups similar textures for effective decoder sharing; and (4) comprehensive performance and ablation studies validating our approach.

Related papers

• ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization [59.481950697968706]
  We propose Progressive Generative Image Compression (ProGIC), a compact built on residual vector quantization (RVQ)<n>In RVQ, a sequence of vector quantizers encodes the residuals stage by stage, each with its own codebook.<n>We pair this with a lightweight backbone based on depthwise-separable convolutions and small attention blocks, enabling practical deployment on both GPU and CPU-only devices.
  arXiv  Detail & Related papers  (2026-03-03T11:47:05Z)
• VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction [55.66673587952058]
  Video understanding models are increasingly limited by the prohibitive storage and computational costs of large-scale datasets.<n>VideoCompressa is a novel framework for video data synthesis that reframes the problem as dynamic latent compression.
  arXiv  Detail & Related papers  (2025-11-24T07:07:58Z)
• GANCompress: GAN-Enhanced Neural Image Compression with Binary Spherical Quantization [0.0]
  GANCompress is a novel neural compression framework that combines Binary Spherical Quantization (BSQ) with Generative Adversarial Networks (GANs)<n>We show that GANCompress achieves substantial improvement in compression efficiency -- reducing file sizes by up to 100x with minimal visual distortion.
  arXiv  Detail & Related papers  (2025-05-19T00:18:27Z)
• Neural Graphics Texture Compression Supporting Random Access [34.974631096947284]
  We introduce a novel approach to texture set compression that integrates traditional GPU texture representation and NIC techniques. We propose an asymmetric auto-encoder framework that employs a convolutional encoder to capture detailed information in a bottleneck-latent space. Experimental results demonstrate that this approach provides much better results than conventional texture compression.
  arXiv  Detail & Related papers  (2024-05-06T19:44:13Z)
• You Can Mask More For Extremely Low-Bitrate Image Compression [80.7692466922499]
  Learned image compression (LIC) methods have experienced significant progress during recent years. LIC methods fail to explicitly explore the image structure and texture components crucial for image compression. We present DA-Mask that samples visible patches based on the structure and texture of original images. We propose a simple yet effective masked compression model (MCM), the first framework that unifies LIC and LIC end-to-end for extremely low-bitrate compression.
  arXiv  Detail & Related papers  (2023-06-27T15:36:22Z)
• Random-Access Neural Compression of Material Textures [1.2971248363246106]
  We propose a novel neural compression technique specifically designed for material textures. We unlock two more levels of detail, i.e., 16x more texels, using low compression. Our method allows on-demand, real-time decompression with random access, enabling compression on disk and memory.
  arXiv  Detail & Related papers  (2023-05-26T17:16:22Z)
• Towards Compact CNNs via Collaborative Compression [166.86915086497433]
  We propose a Collaborative Compression scheme, which joints channel pruning and tensor decomposition to compress CNN models. We achieve 52.9% FLOPs reduction by removing 48.4% parameters on ResNet-50 with only a Top-1 accuracy drop of 0.56% on ImageNet 2012.
  arXiv  Detail & Related papers  (2021-05-24T12:07:38Z)
• Conditional Entropy Coding for Efficient Video Compression [82.35389813794372]
  We propose a very simple and efficient video compression framework that only focuses on modeling the conditional entropy between frames. We first show that a simple architecture modeling the entropy between the image latent codes is as competitive as other neural video compression works and video codecs. We then propose a novel internal learning extension on top of this architecture that brings an additional 10% savings without trading off decoding speed.
  arXiv  Detail & Related papers  (2020-08-20T20:01:59Z)
• Deep Implicit Volume Compression [33.81053554523246]
  We describe a novel approach for compressing truncated signed distance fields stored in 3D voxel grids. Our method relies on a block-based neural network architecture trained end-to-end, achieving state-of-the-art rate-distortion trade-off.
  arXiv  Detail & Related papers  (2020-05-18T16:46:13Z)
• 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)
• Improved Image Coding Autoencoder With Deep Learning [8.92071749364712]
  We build autoencoder based pipelines for extreme end-to-end image compression based on Ball'e's approach. It achieved around 4.0% reduction in bits per pixel (bpp), 0.03% increase in multi-scale structural similarity (MS-SSIM) and only 0.47% decrease in peak signal-to-noise ratio (PSNR)
  arXiv  Detail & Related papers  (2020-02-28T03:21:47Z)

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.