arXiv subjects

Ahmet Bilican

Publications and source records attributed to Ahmet Bilican.

7 recordsLinked to original sources

arXiv2026

Edit2Restore:Few-Shot Image Restoration via Parameter-Efficient Adaptation of Pre-trained Editing Models

Image restoration has traditionally required training specialized models on thousands of paired examples per degradation type. Large pre-trained text-conditioned image editing models encode rich priors about image structure, quality, and degradation, yet we find that this knowledge does not, on its own, make them restorers: state-of-the-art editing models largely fail at restoration in the zero-shot regime. We show that what these priors lack is not capability but direction, and that a small amount of parameter-efficient adaptation supplies it. Fine-tuning LoRA adapters on FLUX.1 Kontext, a 12B-parameter flow matching model for image-to-image translation, with only 32--128 paired images per task and guided by simple text prompts, we turn a mediocre zero-shot editor into a competitive restorer. A single unified adapter, conditioned on task-specific prompts, handles five diverse degradations. Despite using three to four orders of magnitude less data, our few-shot model surpasses a recent restoration baseline trained on over a million curated pairs on the majority of perceptual and distribution-level metrics, on which we evaluate in keeping with our focus on perceptual rather than pixel-fidelity quality. Through comprehensive studies, we analyze the impact of training-set size, the trade-off between task-specific and unified multi-task adapters, the effect of text encoder adaptation, and zero-shot baseline performance, establishing pre-trained editing models as a compelling, data-efficient foundation for few-shot, prompt-guided image restoration.

eess.IV↗

arXiv2026

Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision

Efficiently adapting large pretrained models is critical under tight compute and memory budgets. While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA achieve efficiency through low-rank updates, their discrete rank constraint limits fine-grained parameter control and confines adaptations to low-dimensional subspaces. We propose Wavelet Fine-Tuning (WaveFT), which learns sparse updates in the wavelet domain of weight matrices, enabling fine-grained control over trainable parameters well below LoRA's minimum rank. Wavelet bases provide semi-local receptive fields that aggregate spatially coherent gradients, offering better coverage than direct weight sparsity (SHiRA) without the destructive interference of global Fourier bases (FourierFT). We provide theoretical analysis showing: (i) sparse methods achieve high-rank updates, avoiding LoRA's subspace bottleneck and enabling higher representational capacity, and (ii) a gradient coverage framework explaining when WaveFT is preferable. We perform experiments across text-to-image generation, image classification, and language understanding. WaveFT demonstrates state-of-the-art results among PEFT methods for vision tasks, where wavelets effectively capture sparse gradient structure through improved coverage, while performing comparably on NLP tasks. WaveFT has officially been included in the Hugging Face PEFT library (huggingface.co/docs/peft/en/package_reference/waveft).

cs.CV↗

arXiv2025

Content-Adaptive Inference for State-of-the-art Learned Video Compression

While the BD-rate performance of recent learned video codec models in both low-delay and random-access modes exceed that of respective modes of traditional codecs on average over common benchmarks, the performance improvements for individual videos with complex/large motions is much smaller compared to scenes with simple motion. This is related to the inability of a learned encoder model to generalize to motion vector ranges that have not been seen in the training set, which causes loss of performance in both coding of flow fields as well as frame prediction and coding. As a remedy, we propose a generic (model-agnostic) framework to control the scale of motion vectors in a scene during inference (encoding) to approximately match the range of motion vectors in the test and training videos by adaptively downsampling frames. This results in down-scaled motion vectors enabling: i) better flow estimation; hence, frame prediction and ii) more efficient flow compression. We show that the proposed framework for content-adaptive inference improves the BD-rate performance of already state-of-the-art low-delay video codec DCVC-FM by up to 41\% on individual videos without any model fine tuning. We present ablation studies to show measures of motion and scene complexity can be used to predict the effectiveness of the proposed framework.

eess.IV↗

arXiv2025

Image-Difficulty-Aware Evaluation of Super-Resolution Models

Image super-resolution models are commonly evaluated by average scores (over some benchmark test sets), which fail to reflect the performance of these models on images of varying difficulty and that some models generate artifacts on certain difficult images, which is not reflected by the average scores. We propose difficulty-aware performance evaluation procedures to better differentiate between SISR models that produce visually different results on some images but yield close average performance scores over the entire test set. In particular, we propose two image-difficulty measures, the high-frequency index and rotation-invariant edge index, to predict those test images, where a model would yield significantly better visual results over another model, and an evaluation method where these visual differences are reflected on objective measures. Experimental results demonstrate the effectiveness of the proposed image-difficulty measures and evaluation methodology.

cs.CV↗

arXiv2025

DiMoSR: Feature Modulation via Multi-Branch Dilated Convolutions for Efficient Image Super-Resolution

Balancing reconstruction quality versus model efficiency remains a critical challenge in lightweight single image super-resolution (SISR). Despite the prevalence of attention mechanisms in recent state-of-the-art SISR approaches that primarily emphasize or suppress feature maps, alternative architectural paradigms warrant further exploration. This paper introduces DiMoSR (Dilated Modulation Super-Resolution), a novel architecture that enhances feature representation through modulation to complement attention in lightweight SISR networks. The proposed approach leverages multi-branch dilated convolutions to capture rich contextual information over a wider receptive field while maintaining computational efficiency. Experimental results demonstrate that DiMoSR outperforms state-of-the-art lightweight methods across diverse benchmark datasets, achieving superior PSNR and SSIM metrics with comparable or reduced computational complexity. Through comprehensive ablation studies, this work not only validates the effectiveness of DiMoSR but also provides critical insights into the interplay between attention mechanisms and feature modulation to guide future research in efficient network design. The code and model weights to reproduce our results are available at: https://github.com/makinyilmaz/DiMoSR

cs.CV↗

arXiv2025

FG-DFPN: Flow Guided Deformable Frame Prediction Network

Video frame prediction remains a fundamental challenge in computer vision with direct implications for autonomous systems, video compression, and media synthesis. We present FG-DFPN, a novel architecture that harnesses the synergy between optical flow estimation and deformable convolutions to model complex spatio-temporal dynamics. By guiding deformable sampling with motion cues, our approach addresses the limitations of fixed-kernel networks when handling diverse motion patterns. The multi-scale design enables FG-DFPN to simultaneously capture global scene transformations and local object movements with remarkable precision. Our experiments demonstrate that FG-DFPN achieves state-of-the-art performance on eight diverse MPEG test sequences, outperforming existing methods by 1dB PSNR while maintaining competitive inference speeds. The integration of motion cues with adaptive geometric transformations makes FG-DFPN a promising solution for next-generation video processing systems that require high-fidelity temporal predictions. The model and instructions to reproduce our results will be released at: https://github.com/KUIS-AI-Tekalp-Research Group/frame-prediction

eess.IV↗

arXiv2024

Motion-Adaptive Inference for Flexible Learned B-Frame Compression

While the performance of recent learned intra and sequential video compression models exceed that of respective traditional codecs, the performance of learned B-frame compression models generally lag behind traditional B-frame coding. The performance gap is bigger for complex scenes with large motions. This is related to the fact that the distance between the past and future references vary in hierarchical B-frame compression depending on the level of hierarchy, which causes motion range to vary. The inability of a single B-frame compression model to adapt to various motion ranges causes loss of performance. As a remedy, we propose controlling the motion range for flow prediction during inference (to approximately match the range of motions in the training data) by downsampling video frames adaptively according to amount of motion and level of hierarchy in order to compress all B-frames using a single flexible-rate model. We present state-of-the-art BD rate results to demonstrate the superiority of our proposed single-model motion-adaptive inference approach to all existing learned B-frame compression models.

eess.IV↗