Runyu Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Runyu Yang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Ivan V. Bajic
School of Engineering Science Simon Fraser University Burnaby BC Canada
2 shared publications - Alon Harell
Simon Fraser University Burnaby BC Canada
1 shared publication - Fabien Racape
InterDigital -AI Lab
1 shared publication - Hyomin Choi
InterDigital AI Lab Los Altos Aachen CA USA Germany
1 shared publication - Masoud Khairi Atani
Simon Fraser University Burnaby BC Canada
1 shared publication
Latest Publications
- Open Access
How Universal Are SAM2 Features?
The trade-off between general-purpose foundation vision models and their specialized counterparts is critical for efficient feature coding design and is not yet fully understood. We investigate this trade-off by comparing the feature versatility of the general-purpose Hiera encoder against the segmentation-specialized Segment Anything Model 2 (SAM2). Using a lightweight, trainable neck to probe the adaptability of their frozen features, we quantify the information-theoretic cost of specialization. Our results reveal that while SAM2's specialization is highly effective for spatially-related tasks like depth estimation, it comes at a cost. The specialized SAM2 encoder underperforms its generalist predecessor, Hiera, on conceptually distant tasks such as pose estimation and image captioning, demonstrating a measurable loss of broader semantic information. A novel cross-neck analysis on SAM2 reveals that each level of adaptation creates a further representational bottleneck. Our analysis illuminates these trade-offs in feature universality, providing a quantitative foundation for designing efficient feature coding and adaptation strategies for diverse downstream applications.
Open AccessHow Universal Are SAM2 Features?
The trade-off between general-purpose foundation vision models and their specialized counterparts is critical for efficient feature coding design and is not yet fully understood. We investigate this trade-off by comparing the feature versatility of the general-purpose Hiera encoder against the segmentation-specialized Segment Anything Model 2 (SAM2). Using a lightweight, trainable neck to probe the adaptability of their frozen features, we quantify the information-theoretic cost of specialization. Our results reveal that while SAM2's specialization is highly effective for spatially-related tasks like depth estimation, it comes at a cost. The specialized SAM2 encoder underperforms its generalist predecessor, Hiera, on conceptually distant tasks such as pose estimation and image captioning, demonstrating a measurable loss of broader semantic information. A novel cross-neck analysis on SAM2 reveals that each level of adaptation creates a further representational bottleneck. Our analysis illuminates these trade-offs in feature universality, providing a quantitative foundation for designing efficient feature coding and adaptation strategies for diverse downstream applications.
- Open Access
Bit Allocation Transfer for Perceptual Quality Enhancement of VVC Intra Coding
Mainstream image and video coding standards -- including state-of-the-art codecs like H.266/VVC, AVS3, and AV1 -- adopt a block-based hybrid coding framework. While this framework facilitates straightforward optimization for Peak Signal-to-Noise Ratio (PSNR), it struggles to effectively optimize perceptually-aligned metrics such as Multi-Scale Structural Similarity (MS-SSIM). To address this challenge, this paper proposes a low-complexity method to enhance perceptual quality in VVC intra coding by transferring bit allocation knowledge from end-to-end image compression. We introduce a lightweight model trained with perceptual losses to generate a quantization step map. This map implicitly captures block-level perceptual importance, enabling efficient derivation of a QP map for VVC. Experiments on Kodak and CLIC datasets demonstrate significant advantages, both in execution time and perceptual metric performance, with more than 11% BD-rate reduction in terms of MS-SSIM. Our scheme provides an efficient, practical pathway for perceptual enhancement of traditional codecs.
Open AccessBit Allocation Transfer for Perceptual Quality Enhancement of VVC Intra Coding
Mainstream image and video coding standards -- including state-of-the-art codecs like H.266/VVC, AVS3, and AV1 -- adopt a block-based hybrid coding framework. While this framework facilitates straightforward optimization for Peak Signal-to-Noise Ratio (PSNR), it struggles to effectively optimize perceptually-aligned metrics such as Multi-Scale Structural Similarity (MS-SSIM). To address this challenge, this paper proposes a low-complexity method to enhance perceptual quality in VVC intra coding by transferring bit allocation knowledge from end-to-end image compression. We introduce a lightweight model trained with perceptual losses to generate a quantization step map. This map implicitly captures block-level perceptual importance, enabling efficient derivation of a QP map for VVC. Experiments on Kodak and CLIC datasets demonstrate significant advantages, both in execution time and perceptual metric performance, with more than 11% BD-rate reduction in terms of MS-SSIM. Our scheme provides an efficient, practical pathway for perceptual enhancement of traditional codecs.