仅 0.787M 参数！哈工深&清华等提出 TTTIR，刷新图像恢复 12 项 SOTA
Ranking
Overall
62
Content
70
Popularity
42
Observed public metrics from 1 member.
Merged summary
TL;DR - TTTIR reframes image restoration as test-time state evolution, dynamically adapting lightweight operators to each degraded image. With 0.787M parameters, it reports state-of-the-art results across 12 low-light enhancement, deraining, raindrop removal, and dehazing benchmarks.
- A progressive state sequence generator builds coarse-to-fine restoration targets by combining spatial features with wavelet-based frequency states.
- A state transition evolution module performs a single-step fast-weight update during inference, creating an instance-specific restoration operator.
- On cross-dataset LOL-v2-Real evaluation, TTTIR reaches 30.78 dB PSNR and 0.9070 SSIM after training only on LOL-v1.
- Its depthwise-convolution inner loop keeps memory and latency growth roughly linear with image resolution; the implementation is open source.
Sources (1)
仅 0.787M 参数！哈工深&清华等提出 TTTIR，刷新图像恢复 12 项 SOTA
Public signals
OpenAlex citations 0
TL;DR - TTTIR reframes image restoration as test-time state evolution, dynamically adapting lightweight operators to each degraded image. With 0.787M parameters, it reports state-of-the-art results across 12 low-light enhancement, deraining, raindrop removal, and dehazing benchmarks.
- A progressive state sequence generator builds coarse-to-fine restoration targets by combining spatial features with wavelet-based frequency states.
- A state transition evolution module performs a single-step fast-weight update during inference, creating an instance-specific restoration operator.
- On cross-dataset LOL-v2-Real evaluation, TTTIR reaches 30.78 dB PSNR and 0.9070 SSIM after training only on LOL-v1.
- Its depthwise-convolution inner loop keeps memory and latency growth roughly linear with image resolution; the implementation is open source.