Learned image compression has seen significant progress in recent years with the development of end-to-end learned models that achieve better compression efficiency than state-of-the-art conventional methods. Recently, Mixture of Experts (MoE) approaches have seen promising results in NLP and computer vision tasks. In...
Jonas Brenig, R. Timofte· International Conference on...· 1 citation
Modern cameras transform RAW sensor measurements into sRGB images through an image signal processor (ISP). We benchmark two placements for blind restoration around a fixed ISP: (A) pre-ISP restoration in the RAW domain and (B) post-ISP restoration in the sRGB domain. The benchmark covers four smartphone device groups,...
Zi-Hao Lu, R. Timofte, Marcos V. Conde· 0 citations
Embodied systems must make knowledge acquired during one encounter usable in another despite changes in viewpoint, motion, and illumination. Yet aggregate cross-video accuracy conflates failures of local perception with failures to preserve observation identity, establish correspondence, and compose evidence, obscuring...
Yue-Dong Tan, Lei-Tao Qi, Yu Liu et al.· 0 citations
RealDefocus, a benchmark derived from the real-world RealBokeh dataset originally proposed for Bokeh Rendering, is built on, providing paired defocused inputs and sharp ground truth images, predefined training/validation/test splits, and a unified evaluation framework for comparing image restoration and neural renderin...
Tim Seizinger, Zhu-Yun Zhou, R. Timofte· International Conference on...· 0 citations
The Region Token Interface (\method{}) adapts a diffusion model to these tokens, with the region count drawn at random during fine-tuning so one checkpoint serves every budget.
Eduard Zamfir, C. Reisswig, Zong-Wei Wu et al.· 1 citation
Extensive experiments demonstrate that SiConMo achieves a state-of-the-art accuracy-efficiency trade-off among lightweight semantic segmentation models, highlighting simplicity as a powerful design principle.
Mian Muhammad Naeem Abid, Nancy Mehta, Zong-Wei Wu et al.· International Conference on...· 0 citations
TRaM-VSR, a Token Routing and Merging framework for adaptive token allocation, leveraging both context-aware video priors and network-level priors accelerates inference significantly while preserving state-of-the-art reconstruction quality and robust temporal consistency is proposed.
Sicheng Gao, Zhuyun Zhou, Yixuan Liu et al.· arXiv.org· 0 citations
The two studies show that closed-loop GPU fine-tuning does not guarantee monotonic mobile gains, especially on harder classification tasks, and that multi-dataset, on-device measurement is needed to stress-test deployment objectives.
Saif U. Din, M. Hussain, R. Timofte et al.· 0 citations
Direct-copy and negative-control analyses show that gains depend on source-target compatibility and LLM adaptation; stored source accuracy alone does not predict transferability.
Kabir Baghel, R. Timofte, Dmitry Ignatov· 0 citations
Large language models (LLMs) can generate neural-network modifications, but unrestricted generation is often invalid or harmful. This paper studies a narrower setting: improving a weak target model using a stronger same-family source model from a neural-network database. We propose a source-guided candidate-generation...
Kabir Baghel, R. Timofte, Dmitry Ignatov· 0 citations
A cross-dataset transfer observation on SVHN, where direct base-model generation without curriculum warmup yields 27% peak SR at substantially lower accuracy than the CIFAR-10 equivalent, is reported, consistent with the increased synthesis difficulty of the unq-family anchor architecture.
Anujaya Vijayakumar, R. Timofte, Dmitry Ignatov· 0 citations
This dataset defines a new basis for reproducible and data-driven AI design, advancing the emerging paradigm of LLM-driven AutoML and architectural generalization across modalities and hardware.
Tolgay Atinc Uzun, Waleed Khalid, Saif U Din et al.· 19 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
