FreeTransformSR is a lightweight image super‑resolution network that uses a channel‑wise free low‑rank learnable transform to adaptively modulate features with minimal parameters. It adds a local feature modulation branch with depthwise convolution and a soft complexity adaptive module that fuses local convolution and window self‑attention based on texture characteristics. The model also employs an adaptive intensity modulation strategy and achieves competitive PSNR/SSIM on five benchmark datasets while using only 595K parameters and running faster than competing methods.
arXiv:2605.09687v2 Announce Type: replace Abstract: Remote sensing single-image super-resolution aims to generate high-resolution imagery from low-resolution observations while preserving fine struct...
The paper introduces SPARK, a lightweight input‑conditioned controller that modulates only a few dominant channels in frozen Diffusion Transformer (DiT) based super‑resolution models. By predicting bounded per‑channel affine transformations for selected channels, SPARK improves reconstruction fidelity and perceptual quality without fine‑tuning the backbone or adding adapters. Experiments on three DiT‑based SR backbones across DIV2K, RealSR, and DRealSR demonstrate consistent gains while modulating only eight channels per stream and block.
arXiv:2505.16157v3 Announce Type: replace Abstract: Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Tran...
arXiv:2608. 20263v1 Announce Type: new Abstract: We propose UHDformer++, a general Transformer-based framework to solve numerous Ultra-High-Definition (UHD) image restoration tasks.
arXiv:2601.17723v3 Announce Type: replace Abstract: Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). However, no systematic emp...
arXiv:2606. 19617v1 Announce Type: cross Abstract: We present GB-LSR (Global-Bandwidth Local Spectral Representation), a fixed-grid local spectral representation for continuous image reconstruction.
We present GB-LSR (Global-Bandwidth Local Spectral Representation), a fixed-grid local spectral representation for continuous image reconstruction. The image domain is partitioned into non-overlapping square patches, each carrying coefficients for a truncated Fourier basis predicted from shared convolutional-encoder features.
arXiv:2608.30782v1 Announce Type: new Abstract: Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realis...
arXiv:2606. 02092v1 Announce Type: cross Abstract: Semantic segmentation of remote sensing imagery requires models that capture both global context and local detail under tight computational budgets.
arXiv:2607. 03612v1 Announce Type: cross Abstract: Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success.
ProgResViT is an input‑adaptive Vision Transformer that processes images progressively across multiple rounds, starting with a low‑resolution image and a narrow subnetwork and refining the prediction with higher resolution and a wider subnetwork if needed. The method introduces Progress‑Conditioned Soft Gating (PSG) to share a single backbone across rounds while conditioning token fusion and layer outputs on the current round, block, and input resolution. Experiments on DeiT show improved accuracy‑compute trade‑offs compared to adaptive‑width, adaptive‑depth, and dynamic‑token baselines, and the design also benefits self‑supervised DINO representations and downstream semantic segmentation.
Semantic segmentation of remote sensing imagery requires models that capture both global context and local detail under tight computational budgets. Prior work typically optimizes for one of these axes: attention for global context, convolution for local detail, or compactness for efficiency.