Liming Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Liming Liu has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Xinggong Zhang
Wangxuan Institute of Computer Technology, Peking University, Beijing, China
8 shared publications - Jiangkai Wu
Peking University, Beijing, China
7 shared publications - Haoyang Wang
Peking University, Beijing, China
3 shared publications - Peiheng Wang
Peking University, Beijing, China
3 shared publications - Zongming Guo
Peking University, Beijing, China
3 shared publications - Haodan Zhang
Wangxuan Institute of Computer Technology, Peking University, China
2 shared publications
Latest Publications
- Open Access
- 11 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1649-1662
Artic: AI-oriented Real-time Communication for MLLM Video Assistant
- 11 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1649-1662
Open AccessArtic: AI-oriented Real-time Communication for MLLM Video Assistant
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5557-5567
Camel: Frame-Level Bandwidth Estimation for Low-Latency Live Streaming under Video Bitrate Undershooting
Low-latency live streaming (LLS) has emerged as a popular web application, with many platforms adopting real-time protocols such as WebRTC to minimize end-to-end latency. However, we observe a counter-intuitive phenomenon: even when the actual encoded bitrate does not fully utilize the available bandwidth, stalling events remain frequent. This insufficient bandwidth utilization arises from the intrinsic temporal variations of real-time video encoding, which cause conventional packet-level congestion control algorithms to misestimate available bandwidth. When a high-bitrate frame is suddenly produced, sending at the wrong rate can either trigger packet loss or increase queueing delay, resulting in playback stalls. To address these issues, we present Camel, a novel frame-level congestion control algorithm (CCA) tailored for LLS. Our insight is to use frame-level network feedback to capture the true network capacity, immune to the irregular sending pattern caused by encoding. Camel comprises three key modules: the Bandwidth and Delay Estimator and the Congestion Detector, which jointly determine the average sending rate, and the Bursting Length Controller, which governs the emission pattern to prevent packet loss. We evaluate Camel on both large-scale real-world deployments and controlled simulations. In the real-world platform with 250M users and 2B sessions across 150+ countries, Camel achieves up to a 70.8% increase in 1080P resolution ratio, a 14.4% increase in media bitrate, and up to a 14.1% reduction in stalling ratio. In simulations under undershooting, shallow buffers, and network jitter, Camel outperforms existing congestion control algorithms, with up to 19.8% higher bitrate, 93.0% lower stalling ratio, and 23.9% improvement in bandwidth estimation accuracy.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5557-5567
Open AccessCamel: Frame-Level Bandwidth Estimation for Low-Latency Live Streaming under Video Bitrate Undershooting
Low-latency live streaming (LLS) has emerged as a popular web application, with many platforms adopting real-time protocols such as WebRTC to minimize end-to-end latency. However, we observe a counter-intuitive phenomenon: even when the actual encoded bitrate does not fully utilize the available bandwidth, stalling events remain frequent. This insufficient bandwidth utilization arises from the intrinsic temporal variations of real-time video encoding, which cause conventional packet-level congestion control algorithms to misestimate available bandwidth. When a high-bitrate frame is suddenly produced, sending at the wrong rate can either trigger packet loss or increase queueing delay, resulting in playback stalls. To address these issues, we present Camel, a novel frame-level congestion control algorithm (CCA) tailored for LLS. Our insight is to use frame-level network feedback to capture the true network capacity, immune to the irregular sending pattern caused by encoding. Camel comprises three key modules: the Bandwidth and Delay Estimator and the Congestion Detector, which jointly determine the average sending rate, and the Bursting Length Controller, which governs the emission pattern to prevent packet loss. We evaluate Camel on both large-scale real-world deployments and controlled simulations. In the real-world platform with 250M users and 2B sessions across 150+ countries, Camel achieves up to a 70.8% increase in 1080P resolution ratio, a 14.4% increase in media bitrate, and up to a 14.1% reduction in stalling ratio. In simulations under undershooting, shallow buffers, and network jitter, Camel outperforms existing congestion control algorithms, with up to 19.8% higher bitrate, 93.0% lower stalling ratio, and 23.9% improvement in bandwidth estimation accuracy.
- Open Access
- 4 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 120-126
HybridPrompt: Bridging Generative Priors and Traditional Codecs for Mobile Streaming
- 4 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 120-126
Open AccessHybridPrompt: Bridging Generative Priors and Traditional Codecs for Mobile Streaming
- Open Access
- 17 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 402-410
Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI
- 17 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 402-410
Open AccessChat with AI: The Surprising Turn of Real-time Video Communication from Human to AI
- Open Access
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Gecko: High-Quality Video Streaming via Generative Prompt Chunks
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessGecko: High-Quality Video Streaming via Generative Prompt Chunks
- Open Access
- 6 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 178-184
PromptMobile: Efficient Promptus for Low Bandwidth Mobile Video Streaming
- 6 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 178-184
Open AccessPromptMobile: Efficient Promptus for Low Bandwidth Mobile Video Streaming
- Open Access
- 4 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 39-44
Low-bitrate Volumetric Video Streaming with Depth Image
Volumetric video, which is six-degrees-of-freedom (6D0F), serves an immersive viewing experience. However, the high bandwidth required for streaming volumetric video over networks presents challenges for its flourishing. To address this issue, we propose a novel streaming system that leverages depth image to convert 3D volumetric videos into 2D videos with low bitrate and high fps. Our system addresses two technical challenges when using depth image. Specifically, we use nonlinear regression to solve the virtual camera placement problem and the problem of how to allocate bitrate between color image and depth map when encoding. Evaluations show that our system outperforms existing volumetric video streaming methods and saves 50%-99% bandwidth under the same level of quality.
- 4 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 39-44
Open AccessLow-bitrate Volumetric Video Streaming with Depth Image
Volumetric video, which is six-degrees-of-freedom (6D0F), serves an immersive viewing experience. However, the high bandwidth required for streaming volumetric video over networks presents challenges for its flourishing. To address this issue, we propose a novel streaming system that leverages depth image to convert 3D volumetric videos into 2D videos with low bitrate and high fps. Our system addresses two technical challenges when using depth image. Specifically, we use nonlinear regression to solve the virtual camera placement problem and the problem of how to allocate bitrate between color image and depth map when encoding. Evaluations show that our system outperforms existing volumetric video streaming methods and saves 50%-99% bandwidth under the same level of quality.
- Open Access
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
ActRay: Online Active Ray Sampling for Radiance Fields
Thanks to the high-quality reconstruction and photorealistic rendering, the Neural Radiance Field (NeRF) has garnered extensive attention and has been continuously improved. Despite its high visual quality, the prohibitive training time limits its practical application. Although significant acceleration has been achieved, it is still far from real-time training, due to the need for tens of thousands of iterations. In this paper, a feasible solution is to reduce the number of required iterations by always training the rays with the highest loss values, instead of the traditional method of training each ray with a uniform probability. To this end, we propose an online active ray sampling strategy, ActRay. Specifically, to avoid the substantial overhead of calculating the actual loss values for all rays in each iteration, a rendering-gradient-based loss propagation algorithm is presented to efficiently estimate the loss values. To further narrow the gap between the estimated loss and the actual loss, an online learning algorithm based on the Upper Confidence Bound (UCB) is proposed to control the sampling probability of the rays, thereby compensating for the bias in loss estimation. We evaluate ActRay on both real-world and synthetic scenes, and the promising results show that it accelerates radiance field training by 6.5x. Besides, we test ActRay under all kinds of radiance field representations (implicit, explicit, and hybrid), proving that it is general and effective to different representations. We believe this work will contribute to the practical application of radiance fields, because it has taken a step closer to real-time radiance field training. ActRay is open-source at: https://pku-netvideo.github.io/actray/.
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessActRay: Online Active Ray Sampling for Radiance Fields
Thanks to the high-quality reconstruction and photorealistic rendering, the Neural Radiance Field (NeRF) has garnered extensive attention and has been continuously improved. Despite its high visual quality, the prohibitive training time limits its practical application. Although significant acceleration has been achieved, it is still far from real-time training, due to the need for tens of thousands of iterations. In this paper, a feasible solution is to reduce the number of required iterations by always training the rays with the highest loss values, instead of the traditional method of training each ray with a uniform probability. To this end, we propose an online active ray sampling strategy, ActRay. Specifically, to avoid the substantial overhead of calculating the actual loss values for all rays in each iteration, a rendering-gradient-based loss propagation algorithm is presented to efficiently estimate the loss values. To further narrow the gap between the estimated loss and the actual loss, an online learning algorithm based on the Upper Confidence Bound (UCB) is proposed to control the sampling probability of the rays, thereby compensating for the bias in loss estimation. We evaluate ActRay on both real-world and synthetic scenes, and the promising results show that it accelerates radiance field training by 6.5x. Besides, we test ActRay under all kinds of radiance field representations (implicit, explicit, and hybrid), proving that it is general and effective to different representations. We believe this work will contribute to the practical application of radiance fields, because it has taken a step closer to real-time radiance field training. ActRay is open-source at: https://pku-netvideo.github.io/actray/.
- Open Access
Principal Component Analysis Based on T$\ell_1$-norm Maximization
Classical principal component analysis (PCA) may suffer from the sensitivity to outliers and noise. Therefore PCA based on $\ell_1$-norm and $\ell_p$-norm ($0 < p < 1$) have been studied. Among them, the ones based on $\ell_p$-norm seem to be most interesting from the robustness point of view. However, their numerical performance is not satisfactory. Note that, although T$\ell_1$-norm is similar to $\ell_p$-norm ($0 < p < 1$) in some sense, it has the stronger suppression effect to outliers and better continuity. So PCA based on T$\ell_1$-norm is proposed in this paper. Our numerical experiments have shown that its performance is superior than PCA-$\ell_p$ and $\ell_p$SPCA as well as PCA, PCA-$\ell_1$ obviously.Open AccessPrincipal Component Analysis Based on T$\ell_1$-norm Maximization
Classical principal component analysis (PCA) may suffer from the sensitivity to outliers and noise. Therefore PCA based on $\ell_1$-norm and $\ell_p$-norm ($0 < p < 1$) have been studied. Among them, the ones based on $\ell_p$-norm seem to be most interesting from the robustness point of view. However, their numerical performance is not satisfactory. Note that, although T$\ell_1$-norm is similar to $\ell_p$-norm ($0 < p < 1$) in some sense, it has the stronger suppression effect to outliers and better continuity. So PCA based on T$\ell_1$-norm is proposed in this paper. Our numerical experiments have shown that its performance is superior than PCA-$\ell_p$ and $\ell_p$SPCA as well as PCA, PCA-$\ell_1$ obviously.