Tagged articles

Low-Light Enhancement

2 articles · Page 1 of 1
Data Party THU
Data Party THU
Sep 17, 2026 · Artificial Intelligence

TTTIR: Instance-Specific State Evolution for Image Restoration via Test-Time Training

TTTIR introduces a test-time training framework that models image restoration as progressive instance-specific state evolution, using a Progressive State Sequence Generator for target trajectories and a State Transition Evolver for adaptive operator updates, achieving state-of-the-art results on low-light enhancement, deraining, and dehazing benchmarks with minimal parameters.

DehazingDerainingInstance-Specific Adaptation
0 likes · 9 min read
TTTIR: Instance-Specific State Evolution for Image Restoration via Test-Time Training
AIWalker
AIWalker
Apr 6, 2026 · Artificial Intelligence

BIPNet: Adaptive Progressive Upsampling Drives a Leap in Burst Image Restoration (TPAMI 2025)

The TPAMI 2025 paper introduces BIPNet, a unified burst‑image framework that tackles alignment, fusion, and upsampling challenges with edge‑enhanced alignment, pseudo‑burst feature fusion, and adaptive group upsampling, achieving state‑of‑the‑art results across super‑resolution, low‑light enhancement, and denoising while offering lightweight mobile variants.

BIPNetBurst Image ProcessingDenoising
0 likes · 13 min read
BIPNet: Adaptive Progressive Upsampling Drives a Leap in Burst Image Restoration (TPAMI 2025)