5 papers · 1 filter
Learning Video Dynamics with Predictive Differentiable Rendering
Yujin Tang, Tian Zhou, Xin Lin +5
How to accurately predict a high-fidelity future world? While the visual world is inherently continuous, existing deterministic video prediction models operate in discrete pixel sp…
MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
Luyuan Zhang, Siyuan Li, Zedong Wang +7
Most visual tokenizers for image generation are bifurcated into two families with complementary limitations: continuous VAEs offer high-fidelity reconstruction but suffer from dens…
Distributed Image Compression with Multimodal Side Information at Extremely Low Bitrates
Guojun Xu, Mingyang Zhang, Jianwen Xiang +3
Distributed Image Compression (DIC) is crucial for multi-view transmission, especially when operating at extremely low bitrates (< 0.1 bpp). Its core challenge is effectively utili…
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
Siyong Jian, Siyuan Li, Luyuan Zhang +5
Discrete autoregressive (AR) text-to-image (T2I) models pair a VQ tokenizer with an AR policy, and current post-training pipelines optimize only the policy while keeping the VQ dec…
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Siyuan Li, Luyuan Zhang, Zedong Wang +8
Masked Image Modeling (MIM) with Vector Quantization (VQ) has achieved great success in both self-supervised pre-training and image generation. However, most existing methods strug…