MambaVideo for Discrete Video Tokenization with Channel-Split Quantization

• URL: http://arxiv.org/abs/2507.04559v1
• Date: Sun, 06 Jul 2025 22:23:27 GMT
• Title: MambaVideo for Discrete Video Tokenization with Channel-Split Quantization
• Authors: Dawit Mureja Argaw, Xian Liu, Joon Son Chung, Ming-Yu Liu, Fitsum Reda,
• Abstract summary: This work introduces a state-of-the-art discrete video tokenizer with two key contributions.<n>First, we propose a novel Mamba-based encoder-decoder architecture that overcomes the limitations of previous sequencebased tokenizers.<n>Second, we introduce a new quantization scheme, channel-split quantization, which significantly enhances the representational power of quantized latents.
• Score: 34.23941517563312
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Discrete video tokenization is essential for efficient autoregressive generative modeling due to the high dimensionality of video data. This work introduces a state-of-the-art discrete video tokenizer with two key contributions. First, we propose a novel Mamba-based encoder-decoder architecture that overcomes the limitations of previous sequencebased tokenizers. Second, we introduce a new quantization scheme, channel-split quantization, which significantly enhances the representational power of quantized latents while preserving the token count. Our model sets a new state-of-the-art, outperforming both causal 3D convolutionbased and Transformer-based approaches across multiple datasets. Experimental results further demonstrate its robustness as a tokenizer for autoregressive video generation.

Related papers

• LoViC: Efficient Long Video Generation with Context Compression [68.22069741704158]
  We introduce LoViC, a DiT-based framework trained on million-scale open-domain videos.<n>At the core of our approach is FlexFormer, an expressive autoencoder that jointly compresses video and text into unified latent representations.
  arXiv  Detail & Related papers  (2025-07-17T09:46:43Z)
• Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers [31.95947876513405]
  We present QDi-VT, a quantization framework specifically designed for video DiT models.<n>From the quantization perspective, we propose the Token-aware Quantization Estor (TQE), which compensates for quantization errors in both the token and feature dimensions.<n>Our W3A6 QDi-VT achieves a scene consistency of 23.40, setting a new benchmark and outperforming current state-of-the-art quantization methods by 1.9$times$.
  arXiv  Detail & Related papers  (2025-05-28T09:33:52Z)
• Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models [50.214593234229255]
  We introduce the novel task of Extreme Short Token Reduction, which aims to represent entire videos using a minimal set of discrete tokens.<n>On the Extreme Short Token Reduction task, our VQToken compresses sequences to just 0.07 percent of their original length while incurring only a 0.66 percent drop in accuracy on the NextQA-MC benchmark.
  arXiv  Detail & Related papers  (2025-03-21T09:46:31Z)
• Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation [63.89280381800457]
  We propose TokenBridge, which maintains the strong representation capacity of continuous tokens while preserving the modeling simplicity of discrete tokens.<n>We introduce a dimension-wise quantization strategy that independently discretizes each feature dimension, paired with a lightweight autoregressive prediction mechanism.<n>Our approach achieves reconstruction and generation quality on par with continuous methods while using standard categorical prediction.
  arXiv  Detail & Related papers  (2025-03-20T17:59:59Z)
• Token-Efficient Long Video Understanding for Multimodal LLMs [101.70681093383365]
  STORM is a novel architecture incorporating a dedicated temporal encoder between the image encoder and the Video-LLMs.<n>We show that STORM achieves state-of-the-art results across various long video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-03-06T06:17:38Z)
• 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)
• Adapting Image-to-Video Diffusion Models for Large-Motion Frame Interpolation [0.0]
  We present a conditional encoder designed to adapt an image-to-video model for a large-motion frame.<n>To enhance performance, we integrate a dual-branch feature extractor and propose a cross-frame attention mechanism.<n>Our approach demonstrates superior performance on the Fr'teche Video Distance metric when evaluated against other state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-12-22T14:49:55Z)
• VidTok: A Versatile and Open-Source Video Tokenizer [24.018360305535307]
  VidTok is a versatile video tokenizer that delivers state-of-the-art performance in both continuous and discrete tokenizations.<n>By integrating these advancements, VidTok achieves substantial improvements over existing methods.
  arXiv  Detail & Related papers  (2024-12-17T16:27:11Z)
• MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion [3.7270979204213446]
  We present four key contributions to address the challenges of video processing.<n>First, we introduce the 3D Inverted Vector-Quantization Variencoenco Autocoder.<n>Second, we present MotionAura, a text-to-video generation framework.<n>Third, we propose a spectral transformer-based denoising network.<n>Fourth, we introduce a downstream task of Sketch Guided Videopainting.
  arXiv  Detail & Related papers  (2024-10-10T07:07:56Z)
• SIGMA:Sinkhorn-Guided Masked Video Modeling [69.31715194419091]
  Sinkhorn-guided Masked Video Modelling ( SIGMA) is a novel video pretraining method. We distribute features of space-time tubes evenly across a limited number of learnable clusters. Experimental results on ten datasets validate the effectiveness of SIGMA in learning more performant, temporally-aware, and robust video representations.
  arXiv  Detail & Related papers  (2024-07-22T08:04:09Z)
• ResQ: Residual Quantization for Video Perception [18.491197847596283]
  We propose a novel quantization scheme for video networks coined as Residual Quantization. We extend our model to dynamically adjust the bit-width proportional to the amount of changes in the video.
  arXiv  Detail & Related papers  (2023-08-18T12:41:10Z)
• All in One: Exploring Unified Video-Language Pre-training [44.22059872694995]
  We introduce an end-to-end video-language model, namely textitall-in-one Transformer, that embeds raw video and textual signals into joint representations. The code and pretrained model have been released in https://github.com/showlab/all-in-one.
  arXiv  Detail & Related papers  (2022-03-14T17:06:30Z)
• 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)

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.