Geometric Transformation-Embedded Mamba for Learned Video Compression

• URL: http://arxiv.org/abs/2603.07912v1
• Date: Mon, 09 Mar 2026 03:14:07 GMT
• Title: Geometric Transformation-Embedded Mamba for Learned Video Compression
• Abstract summary: We introduce a video compression framework founded on a direct transform strategy, i.e., nonlinear transform, quantization, and entropy coding.<n>Our method outperforms state-of-the-art video compression approaches in terms of perceptual quality and temporal consistency under low-bitrate constraints.
• Score: 5.89272315125701
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although learned video compression methods have exhibited outstanding performance, most of them typically follow a hybrid coding paradigm that requires explicit motion estimation and compensation, resulting in a complex solution for video compression. In contrast, we introduce a streamlined yet effective video compression framework founded on a direct transform strategy, i.e., nonlinear transform, quantization, and entropy coding. We first develop a cascaded Mamba module (CMM) with different embedded geometric transformations to effectively explore both long-range spatial and temporal dependencies. To improve local spatial representation, we introduce a locality refinement feed-forward network (LRFFN) that incorporates a hybrid convolution block based on difference convolutions. We integrate the proposed CMM and LRFFN into the encoder and decoder of our compression framework. Moreover, we present a conditional channel-wise entropy model that effectively utilizes conditional temporal priors to accurately estimate the probability distributions of current latent features. Extensive experiments demonstrate that our method outperforms state-of-the-art video compression approaches in terms of perceptual quality and temporal consistency under low-bitrate constraints. Our source codes and models will be available at https://github.com/cshw2021/GTEM-LVC.

Related papers

• Generation Is Compression: Zero-Shot Video Coding via Stochastic Rectified Flow [1.8898767128464697]
  emphGenerative Video Codebook Codec (GVCC) is a zero-shot framework that turns a pretrained video generative model into the itself.<n>Building on this unified backbone, we instantiate three conditioning strategies -- emphImage-to-Video (I2V), emphText-to-Video (T2V) and emphFirst-Last-Frame-to-Video (FLF2V)
  arXiv  Detail & Related papers  (2026-03-27T16:33:20Z)
• Content Adaptive based Motion Alignment Framework for Learned Video Compression [72.13599533975413]
  This paper proposes a content adaptive based motion alignment framework.<n>We first introduce a two-stage flow-guided deformable warping mechanism that refines motion compensation with coarse-to-fine offset prediction and mask modulation.<n>Second, we propose a multi-reference quality aware strategy that adjusts distortion weights based on reference quality, and applies it to hierarchical training to reduce error propagation.<n>Third, we integrate a training-free module that downsamples frames by motion magnitude and resolution to obtain smooth motion estimation.
  arXiv  Detail & Related papers  (2025-12-15T02:51:47Z)
• Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression [90.59962443790593]
  In this paper, we present a variable-rate image compression model based on invertible transform to overcome limitations.<n> Specifically, we design a lightweight multi-scale invertible neural network, which maps the input image into multi-scale latent representations.<n> Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared to existing variable-rate methods.
  arXiv  Detail & Related papers  (2025-03-27T09:08:39Z)
• Rethinking Video Tokenization: A Conditioned Diffusion-based Approach [58.164354605550194]
  New tokenizer, Diffusion Conditioned-based Gene Tokenizer, replaces GAN-based decoder with conditional diffusion model.<n>We trained using only a basic MSE diffusion loss for reconstruction, along with KL term and LPIPS perceptual loss from scratch.<n>Even a scaled-down version of CDT (3$times inference speedup) still performs comparably with top baselines.
  arXiv  Detail & Related papers  (2025-03-05T17:59:19Z)
• IBVC: Interpolation-driven B-frame Video Compression [68.18440522300536]
  B-frame video compression aims to adopt bi-directional motion estimation and motion compensation (MEMC) coding for middle frame reconstruction. Previous learned approaches often directly extend neural P-frame codecs to B-frame relying on bi-directional optical-flow estimation. We propose a simple yet effective structure called Interpolation-B-frame Video Compression (IBVC) to address these issues.
  arXiv  Detail & Related papers  (2023-09-25T02:45:51Z)
• Spatial-Temporal Transformer based Video Compression Framework [44.723459144708286]
  We propose a novel Spatial-Temporal Transformer based Video Compression (STT-VC) framework. It contains a Relaxed Deformable Transformer (RDT) with Uformer based offsets estimation for motion estimation and compensation, a Multi-Granularity Prediction (MGP) module based on multi-reference frames for prediction refinement, and a Spatial Feature Distribution prior based Transformer (SFD-T) for efficient temporal-spatial joint residual compression. Experimental results demonstrate that our method achieves the best result with 13.5% BD-Rate saving over VTM.
  arXiv  Detail & Related papers  (2023-09-21T09:23:13Z)
• MMVC: Learned Multi-Mode Video Compression with Block-based Prediction Mode Selection and Density-Adaptive Entropy Coding [21.147001610347832]
  We propose a multi-mode video compression framework that selects the optimal mode for feature domain prediction adapting to different motion patterns. For entropy coding, we consider both dense and sparse post-quantization residual blocks, and apply optional run-length coding to sparse residuals to improve the compression rate. Compared with state-of-the-art video compression schemes and standard codecs, our method yields better or competitive results measured with PSNR and MS-SSIM.
  arXiv  Detail & Related papers  (2023-04-05T07:37:48Z)
• Scene Matters: Model-based Deep Video Compression [13.329074811293292]
  We propose a model-based video compression (MVC) framework that regards scenes as the fundamental units for video sequences. Our proposed MVC directly models novel intensity variation of the entire video sequence in one scene, seeking non-redundant representations instead of reducing redundancy. Our method achieves up to a 20% reduction compared to the latest video standard H.266 and is more efficient in decoding than existing video coding strategies.
  arXiv  Detail & Related papers  (2023-03-08T13:15:19Z)
• FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos [5.958701846880935]
  We propose FFNeRV, a novel method for incorporating flow information into frame-wise representations to exploit the temporal redundancy across the frames in videos. With model compression techniques, FFNeRV outperforms widely-used standard video codecs (H.264 and HEVC) and performs on par with state-of-the-art video compression algorithms.
  arXiv  Detail & Related papers  (2022-12-23T12:51:42Z)
• Learned Video Compression via Heterogeneous Deformable Compensation Network [78.72508633457392]
  We propose a learned video compression framework via heterogeneous deformable compensation strategy (HDCVC) to tackle the problems of unstable compression performance. More specifically, the proposed algorithm extracts features from the two adjacent frames to estimate content-Neighborhood heterogeneous deformable (HetDeform) kernel offsets. Experimental results indicate that HDCVC achieves superior performance than the recent state-of-the-art learned video compression approaches.
  arXiv  Detail & Related papers  (2022-07-11T02:31:31Z)
• 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.