RCENet: Recursive Concatenation and Enhancement Network for Real-Time Super-Resolution
Bibliographic record
Abstract
Recent advancements in edge AI have increased demand for real-time vision models that run efficiently on edge devices. However, their architectural heterogeneity in terms of compute structure, memory bandwidth, and supported tasks requires a vision model optimized for each edge device. Therefore, we present the Recursive Concatenation and Enhancement Network (RCENet), a lightweight and efficient Single Image Super-Resolution (SISR) model optimized for Google Tensor Processing Units (TPUs). To optimize the architecture for Google TPUs, we first conduct a detailed analysis of computational characteristics and runtime behavior to inform the network design. As a result, RCENet leverages hardware-efficient operators and quantization-friendly modules. We further propose Operator-Selective Quantization (OSQ) combined with Quantization-Aware Distillation (QAD), tailored to the TPU architecture, to enable deployment on integer-only inference engines without compromising perceptual quality. Extensive experiments on standard benchmarks show that RCENet delivers competitive visual quality with significantly reduced latency and power consumption. In particular, RCENet achieves more than 70 FPS on Google TPUs, while maintaining visual quality comparable to that of much more complex models. Our method achieved second place on the Quantized Super-Resolution track of the 2025 Mo-bileAI (MAl) Challenge, demonstrating its effectiveness for real-world deployment. Our project page is available at https://rlghksdbs.github.ioIRCENet/
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".