SCOPE (Semantic COdec Pre-Editing), a conditional image pre-editor that modifies images before compression to improve the bitrate and detection accuracy trade-off, and shows consistent gains across different codec families and detector architectures.
Abstract
Image compression is increasingly used before machine vision systems, yet standard codecs are mainly optimized for human perception rather than downstream task accuracy. We propose SCOPE (Semantic COdec Pre-Editing), a conditional image pre-editor that modifies images before compression to improve the bitrate and detection accuracy trade-off. The model is conditioned on the codec family and compression severity, allowing a single trained network to adapt to multiple compression settings without retraining or loading codec-specific weights. Instead of uniformly preserving the whole image, the pre-editor learns to protect task-relevant regions while simplifying less important background content to improve compressibility. The resulting rate-accuracy curves show consistent gains across different codec families and detector architectures, together with strong transferability to unseen learned and wavelet-based compression families.
Vision Transformers incur high computational costs when processing long visual token sequences. Existing reduction methods typically rank tokens independently and discard those deemed unimportant or redundant. We propose a reconstruction-guided framework for visual token condensation (ReConV), which summarizes the comp...
Xiao-Ya Tang, Shi-Long Liu, Daniel Smolyak et al.· 0 citations
FocusVTC, which combines compressed low-DPI global views with selective region enhancement, integrating enhanced views into ongoing reasoning, is introduced, which breaks this trade-off through adaptive resolution while preserving general multimodal capabilities.
Fang-Zhi Zhong, Xue-Rui Qiu, Yu-Qi Pan et al.· arXiv.org· 1 citation
Semantics-Preserving Quantization (SPQ), which gives more calibration weight to concept-sensitive parameters, preserves residual features, and corrects the mean error in video memory, is proposed.
Xi Xiao, Yun-Bei Zhang, Lin Zhao et al.· 0 citations
High-frequency attenuation can reduce the rate of learned image codecs but also remove object boundaries and fine detail. We propose Semantic-Guided Adaptive Latent-Frequency Modulation (SG-AFM), which uses a semantic structural prior to guide attenuation of encoder latents. SG-AFM applies a Haar wavelet transform and...
Gang-Yin Tian, Wen Ji, Alireza Furutanpey et al.· 0 citations
Gen2-VC is proposed, a generative video compression framework that enhances the outputs of learned and conventional codecs with a pretrained video prior, leaving their bitstreams and reference update processes unchanged.
Yin-Huan Huang, Jing-Kai Ying, Pu Chen et al.· 0 citations
Image-token compression must reduce computation without hurting the semantics. We introduce Varest, guided by semantic fungibility: tokens within a coherent semantic region can be summarized coarsely, while object boundaries and literal text require finer distinctions. Object and text localizers guide variable-resoluti...
Tian-Hao Fu, Austin S. Wang, Charles Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.