Mojtaba Bemana

Mojtaba Bemana

Auto-generated profile, based on publicly available information

Mojtaba Bemana

Max‐Planck‐Institut für Informatik Germany

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 August 2022
Verified
Conference Paper
Open access
MBMojtaba Bemana
Mojtaba Bemana
KMKarol Myszkowski
Karol Myszkowski
Jeppe Revall FrisvadJeppe Revall Frisvad
Jeppe Revall Frisvad
HSHans-Peter Seidel
Hans-Peter Seidel
TRTobias Ritschel
Tobias Ritschel
We tackle the problem of generating novel-view images from collections of 2D images showing refractive and reflective objects. Current solutions assume opaque or transparent light transport along straight paths following the emission-absorption model. Instead, we optimize for a field of 3D-varying index of refraction (IoR) and trace light through it that bends toward the spatial gradients of said IoR according to the laws of eikonal light transport.

16 April 2025 in Computer Graphics Forum
Verified
Journal Article
Open access
MBM. Bemana
M. Bemana
TLT. Leimkühler
T. Leimkühler
KMK. Myszkowski
K. Myszkowski
HSH.P. Seidel
H.P. Seidel
TRT. Ritschel
T. Ritschel
We demonstrate generating HDR images using the concerted action of multiple black‐box, pre‐trained LDR image diffusion models. Common diffusion models are not HDR as, first, there is no sufficiently large HDR image dataset available to re‐train them, and, second, even if it was, re‐training such models is impossible for most compute budgets. Instead, we seek inspiration from the HDR image capture literature that traditionally fuses sets of LDR images, called “exposure brackets”, to produce a single HDR image. We operate multiple denoising processes to generate multiple LDR brackets that together form a valid HDR result. To this end, we introduce a brackets consistency term into the diffusion process to couple the brackets such that they agree across the exposure range they share. We demonstrate HDR versions of state‐of‐the‐art unconditional and conditional as well as restoration‐type (LDR2HDR) generative modeling.

13 July 2024
Verified
Conference Paper
Open access
LRLingyan Ruan
Lingyan Ruan
MBMartin Bálint
Martin Bálint
MBMojtaba Bemana
Mojtaba Bemana
KWKrzysztof Wolski
Krzysztof Wolski
HSHans-Peter Seidel
Hans-Peter Seidel
BCBin Chen
Bin Chen
Misfocus is ubiquitous for almost all video producers, degrading video quality and often causing expensive delays and reshoots. Current autofocus (AF) systems are vulnerable to sudden disturbances such as subject movement or lighting changes commonly present in real-world and on-set conditions. Single image defocus deblurring methods are temporally unstable when applied to videos and cannot recover details obscured by temporally varying defocus blur. In this paper, we present an end-to-end solution that allows users to correct misfocus during post-processing. Our method generates and parameterizes defocused videos into sharp layered neural atlases and propagates consistent focus tracking back to the video frames. We introduce a novel differentiable disk blur layer for more accurate point spread function (PSF) simulation, coupled with a circle of confusion (COC) map estimation module with knowledge transferred from the current single image defocus deblurring (SIDD) networks. Our pipeline offers consistent, sharp video reconstruction and effective subject-focus correction and tracking directly on the generated atlases. Furthermore, by adopting our approach, we achieve comparable results to the state-of-the-art optical flow estimation approach from defocus videos.

4 December 2025 in ACM Transactions on Graphics
Verified
Journal Article
Open access
UCUgur Cogalan
Ugur Cogalan
MBMojtaba Bemana
Mojtaba Bemana
KMKarol Myszkowski
Karol Myszkowski
HSHans-Peter Seidel
Hans-Peter Seidel
CGColin Groth
Colin Groth
We present MILO (Metric for Image- and Latent-space Optimization), a lightweight, multiscale, perceptual metric for full-reference image quality assessment (FR-IQA). MILO is trained using pseudo-MOS (Mean Opinion Score) supervision, in which reproducible distortions are applied to diverse images and scored via an ensemble of recent quality metrics that account for visual masking effects. This approach enables accurate learning without requiring large-scale human-labeled datasets. Despite its compact architecture, MILO outperforms existing metrics across standard FR-IQA benchmarks and offers fast inference suitable for real-time applications. Beyond quality prediction, we demonstrate the utility of MILO as a perceptual loss in both image and latent domains. In particular, we show that spatial masking modeled by MILO, when applied to latent representations from a VAE encoder within Stable Diffusion, enables efficient and perceptually aligned optimization. By combining spatial masking with a curriculum learning strategy, we first process perceptually less relevant regions before progressively shifting the optimization to more visually distorted areas. This strategy leads to significantly improved performance in tasks like denoising, super-resolution, and face restoration, while also reducing computational overhead. MILO thus functions as both a state-of-the-art image quality metric and as a practical tool for perceptual optimization in generative pipelines.

23 May 2023 in Computer Graphics Forum
Verified
Journal Article
Open access
UÇU. Çoğalan
U. Çoğalan
MBM. Bemana
M. Bemana
HSHp. Seidel
Hp. Seidel
KMK. Myszkowski
K. Myszkowski

27 April 2024 in Computer Graphics Forum
Verified
Journal Article
Open access
UÇU. Çoğalan
U. Çoğalan
MBM. Bemana
M. Bemana
HSHp. Seidel
Hp. Seidel
KMK. Myszkowski
K. Myszkowski
Full‐reference image quality metrics (FR‐IQMs) aim to measure the visual differences between a pair of reference and distorted images, with the goal of accurately predicting human judgments. However, existing FR‐IQMs, including traditional ones like PSNR and SSIM and even perceptual ones such as HDR‐VDP, LPIPS, and DISTS, still fall short in capturing the complexities and nuances of human perception. In this work, rather than devising a novel IQM model, we seek to improve upon the perceptual quality of existing FR‐IQM methods. We achieve this by considering visual masking, an important characteristic of the human visual system that changes its sensitivity to distortions as a function of local image content. Specifically, for a given FR‐IQM metric, we propose to predict a visual masking model that modulates reference and distorted images in a way that penalizes the visual errors based on their visibility. Since the ground truth visual masks are difficult to obtain, we demonstrate how they can be derived in a self‐supervised manner solely based on mean opinion scores (MOS) collected from an FR‐IQM dataset. Our approach results in enhanced FR‐IQM metrics that are more in line with human prediction both visually and quantitatively.