Duygu Ceylan
Research Subjects
Research Interests
Duygu Ceylan has a total of 90 co-authors. Here are the top co-authors by number of shared publications:
- Erkut Erdem
Hacettepe University
4 shared publications - Hao Li
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
4 shared publications - Anna Frühstück
Adobe Research
3 shared publications - Aykut Erdem
Koc University
3 shared publications - Aysegul Dundar
Bilkent University
3 shared publications - Jimei Yang
Adobe Research
3 shared publications
Latest Publications
- 16 September 2026
- Published by Springer Nature
- p. 75-93
Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-turn Editing
- 16 September 2026
- Published by Springer Nature
- p. 75-93
Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-turn Editing
- 3 August 2026
- Published by Springer Nature
- p. 635-650
PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling
- 3 August 2026
- Published by Springer Nature
- p. 635-650
PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling
- 24 March 2026
- Published by Wiley in Computer Graphics Forum
GeoFusionLRM: Geometry‐Aware Self‐Correction for Consistent 3D Reconstruction
Single‐image 3D reconstruction with large reconstruction models (LRMs) has advanced rapidly, yet reconstructions often exhibit geometric inconsistencies and misaligned details that limit fidelity. We introduce GeoFusionLRM, a geometry‐aware self‐correction framework that leverages the model's own normal and depth predictions to refine structural accuracy. Unlike prior approaches that rely solely on features extracted from the input image, GeoFusionLRM feeds back geometric cues through a dedicated transformer and fusion module, enabling the model to correct errors and enforce consistency with the conditioning image. This design improves the alignment between the reconstructed mesh and the input views without additional supervision or external signals. Extensive experiments demonstrate that GeoFusionLRM achieves sharper geometry, more consistent normals, and higher fidelity than state‐of‐the‐art LRM baselines.
- 24 March 2026
- Published by Wiley in Computer Graphics Forum
GeoFusionLRM: Geometry‐Aware Self‐Correction for Consistent 3D Reconstruction
Single‐image 3D reconstruction with large reconstruction models (LRMs) has advanced rapidly, yet reconstructions often exhibit geometric inconsistencies and misaligned details that limit fidelity. We introduce GeoFusionLRM, a geometry‐aware self‐correction framework that leverages the model's own normal and depth predictions to refine structural accuracy. Unlike prior approaches that rely solely on features extracted from the input image, GeoFusionLRM feeds back geometric cues through a dedicated transformer and fusion module, enabling the model to correct errors and enforce consistency with the conditioning image. This design improves the alignment between the reconstructed mesh and the input views without additional supervision or external signals. Extensive experiments demonstrate that GeoFusionLRM achieves sharper geometry, more consistent normals, and higher fidelity than state‐of‐the‐art LRM baselines.
- Open Access
GeoFusionLRM: Geometry-Aware Self-Correction for Consistent 3D Reconstruction
Single-image 3D reconstruction with large reconstruction models (LRMs) has advanced rapidly, yet reconstructions often exhibit geometric inconsistencies and misaligned details that limit fidelity. We introduce GeoFusionLRM, a geometry-aware self-correction framework that leverages the model's own normal and depth predictions to refine structural accuracy. Unlike prior approaches that rely solely on features extracted from the input image, GeoFusionLRM feeds back geometric cues through a dedicated transformer and fusion module, enabling the model to correct errors and enforce consistency with the conditioning image. This design improves the alignment between the reconstructed mesh and the input views without additional supervision or external signals. Extensive experiments demonstrate that GeoFusionLRM achieves sharper geometry, more consistent normals, and higher fidelity than state-of-the-art LRM baselines.
Open AccessGeoFusionLRM: Geometry-Aware Self-Correction for Consistent 3D Reconstruction
Single-image 3D reconstruction with large reconstruction models (LRMs) has advanced rapidly, yet reconstructions often exhibit geometric inconsistencies and misaligned details that limit fidelity. We introduce GeoFusionLRM, a geometry-aware self-correction framework that leverages the model's own normal and depth predictions to refine structural accuracy. Unlike prior approaches that rely solely on features extracted from the input image, GeoFusionLRM feeds back geometric cues through a dedicated transformer and fusion module, enabling the model to correct errors and enforce consistency with the conditioning image. This design improves the alignment between the reconstructed mesh and the input views without additional supervision or external signals. Extensive experiments demonstrate that GeoFusionLRM achieves sharper geometry, more consistent normals, and higher fidelity than state-of-the-art LRM baselines.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10719-10727
Learned Single-Pass Multitasking Perceptual Graphics for Immersive Displays
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10719-10727
Open AccessLearned Single-Pass Multitasking Perceptual Graphics for Immersive Displays
- Open Access
Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders
Video diffusion models have advanced rapidly in the recent years as a result of series of architectural innovations (e.g., diffusion transformers) and use of novel training objectives (e.g., flow matching). In contrast, less attention has been paid to improving the feature representation power of such models. In this work, we show that training video diffusion models can benefit from aligning the intermediate features of the video generator with feature representations of pre-trained vision encoders. We propose a new metric and conduct an in-depth analysis of various vision encoders to evaluate their discriminability and temporal consistency, thereby assessing their suitability for video feature alignment. Based on the analysis, we present Align4Gen which provides a novel multi-feature fusion and alignment method integrated into video diffusion model training. We evaluate Align4Gen both for unconditional and class-conditional video generation tasks and show that it results in improved video generation as quantified by various metrics. Full video results are available on our project page: https://align4gen.github.io/align4gen/
Open AccessImproving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders
Video diffusion models have advanced rapidly in the recent years as a result of series of architectural innovations (e.g., diffusion transformers) and use of novel training objectives (e.g., flow matching). In contrast, less attention has been paid to improving the feature representation power of such models. In this work, we show that training video diffusion models can benefit from aligning the intermediate features of the video generator with feature representations of pre-trained vision encoders. We propose a new metric and conduct an in-depth analysis of various vision encoders to evaluate their discriminability and temporal consistency, thereby assessing their suitability for video feature alignment. Based on the analysis, we present Align4Gen which provides a novel multi-feature fusion and alignment method integrated into video diffusion model training. We evaluate Align4Gen both for unconditional and class-conditional video generation tasks and show that it results in improved video generation as quantified by various metrics. Full video results are available on our project page: https://align4gen.github.io/align4gen/
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
3D Stylization via Large Reconstruction Model
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open Access3D Stylization via Large Reconstruction Model
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (4) , 1-12
MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills
Retouching is an essential task in post-manipulation of raw photographs. Generative editing, guided by text or strokes, provides a new tool accessible to users but can easily change the identity of the original objects in unacceptable and unpredictable ways. In contrast, although traditional procedural edits, as commonly supported by photoediting tools (e.g., Gimp, Lightroom), are conservative, they are still preferred by professionals. Unfortunately, professional quality retouching involves many individual procedural editing operations that is challenging to plan for most novices. In this paper, we ask if a multimodal large language model (MLLM) can be taught to critique raw photographs, suggest suitable remedies, and finally realize them with a given set of pre-authored procedural image operations. We demonstrate that MLLMs can be first made aware of the underlying image processing operations, by training them to solve specially-designed visual puzzles. Subsequently, such an operation-aware MLLM can both plan and propose edit sequences. To facilitate training, given a set of expert-edited photos, we synthesize a reasoning dataset by procedurally manipulating the expert edits and then grounding a pretrained LLM on the visual adjustments, to synthesize reasoning for finetuning. The proposed retouching operations are, by construction, understandable by the users, preserve object details and resolution, and can be optionally overridden. We evaluate our setup on a variety of test examples and show advantages, in terms of explainability and identity preservation, over existing generative and other procedural alternatives. Code, data, models, and supplementary results can be found via our project website at https://monetgpt.github.io.
- 27 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (4) , 1-12
Open AccessMonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills
Retouching is an essential task in post-manipulation of raw photographs. Generative editing, guided by text or strokes, provides a new tool accessible to users but can easily change the identity of the original objects in unacceptable and unpredictable ways. In contrast, although traditional procedural edits, as commonly supported by photoediting tools (e.g., Gimp, Lightroom), are conservative, they are still preferred by professionals. Unfortunately, professional quality retouching involves many individual procedural editing operations that is challenging to plan for most novices. In this paper, we ask if a multimodal large language model (MLLM) can be taught to critique raw photographs, suggest suitable remedies, and finally realize them with a given set of pre-authored procedural image operations. We demonstrate that MLLMs can be first made aware of the underlying image processing operations, by training them to solve specially-designed visual puzzles. Subsequently, such an operation-aware MLLM can both plan and propose edit sequences. To facilitate training, given a set of expert-edited photos, we synthesize a reasoning dataset by procedurally manipulating the expert edits and then grounding a pretrained LLM on the visual adjustments, to synthesize reasoning for finetuning. The proposed retouching operations are, by construction, understandable by the users, preserve object details and resolution, and can be optionally overridden. We evaluate our setup on a variety of test examples and show advantages, in terms of explainability and identity preservation, over existing generative and other procedural alternatives. Code, data, models, and supplementary results can be found via our project website at https://monetgpt.github.io.
- Open Access
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessHyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation
- Open Access
FloAt: Flow Warping of Self-Attention for Clothing Animation Generation
We propose a diffusion model-based approach, FloAtControlNet to generate cinemagraphs composed of animations of human clothing. We focus on human clothing like dresses, skirts and pants. The input to our model is a text prompt depicting the type of clothing and the texture of clothing like leopard, striped, or plain, and a sequence of normal maps that capture the underlying animation that we desire in the output. The backbone of our method is a normal-map conditioned ControlNet which is operated in a training-free regime. The key observation is that the underlying animation is embedded in the flow of the normal maps. We utilize the flow thus obtained to manipulate the self-attention maps of appropriate layers. Specifically, the self-attention maps of a particular layer and frame are recomputed as a linear combination of itself and the self-attention maps of the same layer and the previous frame, warped by the flow on the normal maps of the two frames. We show that manipulating the self-attention maps greatly enhances the quality of the clothing animation, making it look more natural as well as suppressing the background artifacts. Through extensive experiments, we show that the method proposed beats all baselines both qualitatively in terms of visual results and user study. Specifically, our method is able to alleviate the background flickering that exists in other diffusion model-based baselines that we consider. In addition, we show that our method beats all baselines in terms of RMSE and PSNR computed using the input normal map sequences and the normal map sequences obtained from the output RGB frames. Further, we show that well-established evaluation metrics like LPIPS, SSIM, and CLIP scores that are generally for visual quality are not necessarily suitable for capturing the subtle motions in human clothing animations.
Open AccessFloAt: Flow Warping of Self-Attention for Clothing Animation Generation
We propose a diffusion model-based approach, FloAtControlNet to generate cinemagraphs composed of animations of human clothing. We focus on human clothing like dresses, skirts and pants. The input to our model is a text prompt depicting the type of clothing and the texture of clothing like leopard, striped, or plain, and a sequence of normal maps that capture the underlying animation that we desire in the output. The backbone of our method is a normal-map conditioned ControlNet which is operated in a training-free regime. The key observation is that the underlying animation is embedded in the flow of the normal maps. We utilize the flow thus obtained to manipulate the self-attention maps of appropriate layers. Specifically, the self-attention maps of a particular layer and frame are recomputed as a linear combination of itself and the self-attention maps of the same layer and the previous frame, warped by the flow on the normal maps of the two frames. We show that manipulating the self-attention maps greatly enhances the quality of the clothing animation, making it look more natural as well as suppressing the background artifacts. Through extensive experiments, we show that the method proposed beats all baselines both qualitatively in terms of visual results and user study. Specifically, our method is able to alleviate the background flickering that exists in other diffusion model-based baselines that we consider. In addition, we show that our method beats all baselines in terms of RMSE and PSNR computed using the input normal map sequences and the normal map sequences obtained from the output RGB frames. Further, we show that well-established evaluation metrics like LPIPS, SSIM, and CLIP scores that are generally for visual quality are not necessarily suitable for capturing the subtle motions in human clothing animations.