Wei Jiang
Research Subjects
Wei Jiang has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Wei Wang
Futurewei Technologies Inc., San José, CA, USA
5 shared publications - Zhenghao Chen
University of Newcastle, Newcastle, Australia
5 shared publications - Lebin Zhou
Santa Clara University, Santa Clara, CA, USA
4 shared publications - Dong Xu
The University of Hong Kong, Hong Kong, Hong Kong
2 shared publications - Nam Ling
Santa Clara University
2 shared publications - Cihan Ruan
Department of Computer Science and Engineering, Santa Clara University
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 44-52
Predict-and-Verify Rendering for Dynamic Scenes with Semantic 4D Gaussians
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 44-52
Open AccessPredict-and-Verify Rendering for Dynamic Scenes with Semantic 4D Gaussians
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 71-80
M 3 ISR: A Multi-Modal Multi-View Benchmark for 3D/4D Gaussian Splatting and Feedforward Compression
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 71-80
Open AccessM 3 ISR: A Multi-Modal Multi-View Benchmark for 3D/4D Gaussian Splatting and Feedforward Compression
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 18023-18026
The Fourth International Workshop on Rich Media with Generative AI (RichMediaGAI2026)
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 18023-18026
Open AccessThe Fourth International Workshop on Rich Media with Generative AI (RichMediaGAI2026)
- Open Access
- 26 November 2025
- Published by Springer Nature in Visual Intelligence
- Vol. 3 (1) , 25
TVC: tokenized video compression with ultra-low bit rate
Tokenized visual representations have shown promise in image compression, yet their extension to video remains underexplored due to the challenges posed by complex temporal dynamics and stringent bit rate constraints. In this paper, we present tokenized video compression (TVC), a token-based dual-stream framework designed to operate effectively at ultra-low bit rates. TVC leverages the Cosmos video tokenizer to extract both discrete and continuous token streams. The discrete tokens are partially masked using a strategic masking scheme and then compressed losslessly with a discrete checkerboard context model to reduce transmission overhead. The masked tokens are reconstructed by a decoder-only Transformer with spatiotemporal token prediction. In parallel, the continuous tokens are quantized and compressed using a continuous checkerboard context model, providing complementary continuous information at ultra-low bit rates. At the decoder side, the two streams are fused with a ControlNet-based multi-scale integration module, ensuring high perceptual quality alongside stable fidelity in reconstruction. Overall, this work illustrates the practicality of tokenized video compression and points to new directions for semantics-aware, token-native approaches.
- 26 November 2025
- Published by Springer Nature in Visual Intelligence
- Vol. 3 (1) , 25
Open AccessTVC: tokenized video compression with ultra-low bit rate
Tokenized visual representations have shown promise in image compression, yet their extension to video remains underexplored due to the challenges posed by complex temporal dynamics and stringent bit rate constraints. In this paper, we present tokenized video compression (TVC), a token-based dual-stream framework designed to operate effectively at ultra-low bit rates. TVC leverages the Cosmos video tokenizer to extract both discrete and continuous token streams. The discrete tokens are partially masked using a strategic masking scheme and then compressed losslessly with a discrete checkerboard context model to reduce transmission overhead. The masked tokens are reconstructed by a decoder-only Transformer with spatiotemporal token prediction. In parallel, the continuous tokens are quantized and compressed using a continuous checkerboard context model, providing complementary continuous information at ultra-low bit rates. At the decoder side, the two streams are fused with a ControlNet-based multi-scale integration module, ensuring high perceptual quality alongside stable fidelity in reconstruction. Overall, this work illustrates the practicality of tokenized video compression and points to new directions for semantics-aware, token-native approaches.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14296-14298
(RichMediaGAI'25) 3rd International Workshop on Rich Media with Generative AI
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14296-14298
Open Access(RichMediaGAI'25) 3rd International Workshop on Rich Media with Generative AI
- Open Access
- 26 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 20-29
M 3 VIR: A Large-Scale Multi-Modality Multi-View Synthesized Benchmark Dataset for Image Restoration and Content Creation
- 26 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 20-29
Open AccessM 3 VIR: A Large-Scale Multi-Modality Multi-View Synthesized Benchmark Dataset for Image Restoration and Content Creation
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3010-3018
HybridFlow: Infusing Continuity into Masked Codebook for Extreme Low-Bitrate Image Compression
This paper investigates the challenging problem of learned image compression (LIC) with extreme low bitrates. Previous LIC methods based on transmitting quantized continuous features often yield blurry and noisy reconstruction due to the severe quantization loss. While previous LIC methods based on learned codebooks that discretize visual space usually give poor-fidelity reconstruction due to the insufficient representation power of limited codewords in capturing faithful details. We propose a novel dual-stream framework, HyrbidFlow, which combines the continuous-feature-based and codebook-based streams to achieve both high perceptual quality and high fidelity under extreme low bitrates. The codebook-based stream benefits from the high-quality learned codebook priors to provide high quality and clarity in reconstructed images. The continuous feature stream targets at maintaining fidelity details. To achieve the ultra low bitrate, a masked token-based transformer is further proposed, where we only transmit a masked portion of codeword indices and recover the missing indices through token generation guided by information from the continuous feature stream. We also develop a bridging correction network to merge the two streams in pixel decoding for final image reconstruction, where the continuous stream features rectify biases of the codebook-based pixel decoder to impose reconstructed fidelity details. Experimental results demonstrate superior performance across several datasets under extremely low bitrates, compared with existing single-stream codebook-based or continuous-feature-based LIC methods.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3010-3018
Open AccessHybridFlow: Infusing Continuity into Masked Codebook for Extreme Low-Bitrate Image Compression
This paper investigates the challenging problem of learned image compression (LIC) with extreme low bitrates. Previous LIC methods based on transmitting quantized continuous features often yield blurry and noisy reconstruction due to the severe quantization loss. While previous LIC methods based on learned codebooks that discretize visual space usually give poor-fidelity reconstruction due to the insufficient representation power of limited codewords in capturing faithful details. We propose a novel dual-stream framework, HyrbidFlow, which combines the continuous-feature-based and codebook-based streams to achieve both high perceptual quality and high fidelity under extreme low bitrates. The codebook-based stream benefits from the high-quality learned codebook priors to provide high quality and clarity in reconstructed images. The continuous feature stream targets at maintaining fidelity details. To achieve the ultra low bitrate, a masked token-based transformer is further proposed, where we only transmit a masked portion of codeword indices and recover the missing indices through token generation guided by information from the continuous feature stream. We also develop a bridging correction network to merge the two streams in pixel decoding for final image reconstruction, where the continuous stream features rectify biases of the codebook-based pixel decoder to impose reconstructed fidelity details. Experimental results demonstrate superior performance across several datasets under extremely low bitrates, compared with existing single-stream codebook-based or continuous-feature-based LIC methods.