14 citations · 31 across the 17 of their papers we have counts for
18 papers
ImIR: Image-Instruction Tuning for All-in-One Image Restoration
Süleyman Aslan, Görkay Aydemir, Mısra Yavuz +5
Degradations vary widely across images, so a practical restoration system has to handle many degradation types with one model. A recent and effective recipe adapts a large pretrain…
Leveraging Image Editing Foundation Models for Data-Efficient CT Metal Artifact Reduction
Ahmet Rasim Emirdagi, Süleyman Aslan, Mısra Yavuz +5
Metal artifacts from high-attenuation implants severely degrade CT image quality, obscuring critical anatomical structures and posing a challenge for standard deep learning methods…
Edit2Interp: Adapting Image Foundation Models from Spatial Editing to Video Frame Interpolation with Few-Shot Learning
Nasrin Rahimi, Mısra Yavuz, Burak Can Biner +6
Pre-trained image editing models exhibit strong spatial reasoning and object-aware transformation capabilities acquired from billions of image-text pairs, yet they possess no expli…
Edit2Restore:Few-Shot Image Restoration via Parameter-Efficient Adaptation of Pre-trained Editing Models
Mustafa Akın Yılmaz, Ahmet Bilican, Burak Can Biner +1
Image restoration has traditionally required training specialized models on thousands of paired examples per degradation type. Large pre-trained text-conditioned image editing mode…
Content-Adaptive Inference for State-of-the-art Learned Video Compression
Ahmet Bilican, M. Akın Yılmaz, A. Murat Tekalp
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 c…
DiMoSR: Feature Modulation via Multi-Branch Dilated Convolutions for Efficient Image Super-Resolution
M. Akin Yilmaz, Ahmet Bilican, A. Murat Tekalp
Balancing reconstruction quality versus model efficiency remains a critical challenge in lightweight single image super-resolution (SISR). Despite the prevalence of attention mecha…
Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision
Ahmet Bilican, M. Akın Yılmaz, A. Murat Tekalp +1
Efficiently adapting large pretrained models is critical under tight compute and memory budgets. While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA achieve efficiency t…
FG-DFPN: Flow Guided Deformable Frame Prediction Network
M. Akın Yılmaz, Ahmet Bilican, A. Murat Tekalp
Video frame prediction remains a fundamental challenge in computer vision with direct implications for autonomous systems, video compression, and media synthesis. We present FG-DFP…
The Practice of Averaging Rate-Distortion Curves over Testsets to Compare Learned Video Codecs Can Cause Misleading Conclusions
M. Akin Yilmaz, Onur Keleş, A. Murat Tekalp
This paper aims to demonstrate how the prevalent practice in the learned video compression community of averaging rate-distortion (RD) curves across a test video set can lead to mi…
Motion-Adaptive Inference for Flexible Learned B-Frame Compression
M. Akin Yilmaz, O. Ugur Ulas, Ahmet Bilican +1
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 m…
Multi-Scale Deformable Alignment and Content-Adaptive Inference for Flexible-Rate Bi-Directional Video Compression
M. Akın Yılmaz, O. Ugur Ulas, A. Murat Tekalp
The lack of ability to adapt the motion compensation model to video content is an important limitation of current end-to-end learned video compression models. This paper advances t…
Flexible-Rate Learned Hierarchical Bi-Directional Video Compression With Motion Refinement and Frame-Level Bit Allocation
Eren Cetin, M. Akin Yilmaz, A. Murat Tekalp
This paper presents improvements and novel additions to our recent work on end-to-end optimized hierarchical bi-directional video compression to further advance the state-of-the-ar…
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression
M. Akın Yılmaz, A. Murat Tekalp
Conventional video compression (VC) methods are based on motion compensated transform coding, and the steps of motion estimation, mode and quantization parameter selection, and ent…
Self-Organized Variational Autoencoders (Self-VAE) for Learned Image Compression
M. Akın Yılmaz, Onur Keleş, Hilal Güven +3
In end-to-end optimized learned image compression, it is standard practice to use a convolutional variational autoencoder with generalized divisive normalization (GDN) to transform…
DFPN: Deformable Frame Prediction Network
M. Akın Yılmaz, A. Murat Tekalp
Learned frame prediction is a current problem of interest in computer vision and video compression. Although several deep network architectures have been proposed for learned frame…
On the Computation of PSNR for a Set of Images or Video
Onur Keleş, M. Akın Yılmaz, A. Murat Tekalp +2
When comparing learned image/video restoration and compression methods, it is common to report peak-signal to noise ratio (PSNR) results. However, there does not exist a generally…
Effect of Architectures and Training Methods on the Performance of Learned Video Frame Prediction
M. Akin Yilmaz, A. Murat Tekalp
We analyze the performance of feedforward vs. recurrent neural network (RNN) architectures and associated training methods for learned frame prediction. To this effect, we trained…
End-to-End Rate-Distortion Optimization for Bi-Directional Learned Video Compression
M. Akin Yilmaz, A. Murat Tekalp
Conventional video compression methods employ a linear transform and block motion model, and the steps of motion estimation, mode and quantization parameter selection, and entropy…