Raoul de Charette
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Raoul de Charette has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Fabio Pizzati
INRIA
5 shared publications - Jean-François Lalonde
Université Laval
4 shared publications - Pietro Cerri
VisLab Parma Italy
4 shared publications - Anne Verroust-Blondet
Inria Paris France
3 shared publications Fabio Pizzati
INRIA
3 shared publications- Luis Roldão
Noah’s Ark, Huawei Paris Research Center
3 shared publications
Latest Publications
- 24 July 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (4)
MatSwap: Light‐aware material transfers in images
We present MatSwap, a method to transfer materials to designated surfaces in an image realistically. Such a task is non‐trivial due to the large entanglement of material appearance, geometry, and lighting in a photograph. In the literature, material editing methods typically rely on either cumbersome text engineering or extensive manual annotations requiring artist knowledge and 3D scene properties that are impractical to obtain. In contrast, we propose to directly learn the relationship between the input material—as observed on a flat surface—and its appearance within the scene, without the need for explicit UV mapping. To achieve this, we rely on a custom light‐ and geometry‐aware diffusion model. We fine‐tune a large‐scale pre‐trained text‐to‐image model for material transfer using our synthetic dataset, preserving its strong priors to ensure effective generalization to real images. As a result, our method seamlessly integrates a desired material into the target location in the photograph while retaining the identity of the scene. MatSwap is evaluated on synthetic and real images showing that it compares favorably to recent works. Our code and data are made publicly available on https://github.com/astra‐vision/MatSwap
- 24 July 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (4)
MatSwap: Light‐aware material transfers in images
We present MatSwap, a method to transfer materials to designated surfaces in an image realistically. Such a task is non‐trivial due to the large entanglement of material appearance, geometry, and lighting in a photograph. In the literature, material editing methods typically rely on either cumbersome text engineering or extensive manual annotations requiring artist knowledge and 3D scene properties that are impractical to obtain. In contrast, we propose to directly learn the relationship between the input material—as observed on a flat surface—and its appearance within the scene, without the need for explicit UV mapping. To achieve this, we rely on a custom light‐ and geometry‐aware diffusion model. We fine‐tune a large‐scale pre‐trained text‐to‐image model for material transfer using our synthetic dataset, preserving its strong priors to ensure effective generalization to real images. As a result, our method seamlessly integrates a desired material into the target location in the photograph while retaining the identity of the scene. MatSwap is evaluated on synthetic and real images showing that it compares favorably to recent works. Our code and data are made publicly available on https://github.com/astra‐vision/MatSwap
- 10 April 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (2)
Material transforms from disentangled NeRF representations
In this paper, we first propose a novel method for transferring material transformations across different scenes. Building on disentangled Neural Radiance Field (NeRF) representations, our approach learns to map Bidirectional Reflectance Distribution Functions (BRDF) from pairs of scenes observed in varying conditions, such as dry and wet. The learned transformations can then be applied to unseen scenes with similar materials, therefore effectively rendering the transformation learned with an arbitrary level of intensity. Extensive experiments on synthetic scenes and real‐world objects validate the effectiveness of our approach, showing that it can learn various transformations such as wetness, painting, coating, etc. Our results highlight not only the versatility of our method but also its potential for practical applications in computer graphics. We publish our method implementation, along with our synthetic/real datasets on https://github.com/astra‐vision/BRDFTransform
- 10 April 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (2)
Material transforms from disentangled NeRF representations
In this paper, we first propose a novel method for transferring material transformations across different scenes. Building on disentangled Neural Radiance Field (NeRF) representations, our approach learns to map Bidirectional Reflectance Distribution Functions (BRDF) from pairs of scenes observed in varying conditions, such as dry and wet. The learned transformations can then be applied to unseen scenes with similar materials, therefore effectively rendering the transformation learned with an arbitrary level of intensity. Extensive experiments on synthetic scenes and real‐world objects validate the effectiveness of our approach, showing that it can learn various transformations such as wetness, painting, coating, etc. Our results highlight not only the versatility of our method but also its potential for practical applications in computer graphics. We publish our method implementation, along with our synthetic/real datasets on https://github.com/astra‐vision/BRDFTransform
- Open Access
Domain Adaptation with a Single Vision-Language Embedding
Domain adaptation has been extensively investigated in computer vision but still requires access to target data at the training time, which might be difficult to obtain in some uncommon conditions. In this paper, we present a new framework for domain adaptation relying on a single Vision-Language (VL) latent embedding instead of full target data. First, leveraging a contrastive language-image pre-training model (CLIP), we propose prompt/photo-driven instance normalization (PIN). PIN is a feature augmentation method that mines multiple visual styles using a single target VL latent embedding, by optimizing affine transformations of low-level source features. The VL embedding can come from a language prompt describing the target domain, a partially optimized language prompt, or a single unlabeled target image. Second, we show that these mined styles (i.e., augmentations) can be used for zero-shot (i.e., target-free) and one-shot unsupervised domain adaptation. Experiments on semantic segmentation demonstrate the effectiveness of the proposed method, which outperforms relevant baselines in the zero-shot and one-shot settings.
Open AccessDomain Adaptation with a Single Vision-Language Embedding
Domain adaptation has been extensively investigated in computer vision but still requires access to target data at the training time, which might be difficult to obtain in some uncommon conditions. In this paper, we present a new framework for domain adaptation relying on a single Vision-Language (VL) latent embedding instead of full target data. First, leveraging a contrastive language-image pre-training model (CLIP), we propose prompt/photo-driven instance normalization (PIN). PIN is a feature augmentation method that mines multiple visual styles using a single target VL latent embedding, by optimizing affine transformations of low-level source features. The VL embedding can come from a language prompt describing the target domain, a partially optimized language prompt, or a single unlabeled target image. Second, we show that these mined styles (i.e., augmentations) can be used for zero-shot (i.e., target-free) and one-shot unsupervised domain adaptation. Experiments on semantic segmentation demonstrate the effectiveness of the proposed method, which outperforms relevant baselines in the zero-shot and one-shot settings.
- Open Access
DREAM: Visual Decoding from Reversing Human Visual System
In this work we present DREAM, an fMRI-to-image method for reconstructing viewed images from brain activities, grounded on fundamental knowledge of the human visual system. We craft reverse pathways that emulate the hierarchical and parallel nature of how humans perceive the visual world. These tailored pathways are specialized to decipher semantics, color, and depth cues from fMRI data, mirroring the forward pathways from visual stimuli to fMRI recordings. To do so, two components mimic the inverse processes within the human visual system: the Reverse Visual Association Cortex (R-VAC) which reverses pathways of this brain region, extracting semantics from fMRI data; the Reverse Parallel PKM (R-PKM) component simultaneously predicting color and depth from fMRI signals. The experiments indicate that our method outperforms the current state-of-the-art models in terms of the consistency of appearance, structure, and semantics. Code will be made publicly available to facilitate further research in this field.
Open AccessDREAM: Visual Decoding from Reversing Human Visual System
In this work we present DREAM, an fMRI-to-image method for reconstructing viewed images from brain activities, grounded on fundamental knowledge of the human visual system. We craft reverse pathways that emulate the hierarchical and parallel nature of how humans perceive the visual world. These tailored pathways are specialized to decipher semantics, color, and depth cues from fMRI data, mirroring the forward pathways from visual stimuli to fMRI recordings. To do so, two components mimic the inverse processes within the human visual system: the Reverse Visual Association Cortex (R-VAC) which reverses pathways of this brain region, extracting semantics from fMRI data; the Reverse Parallel PKM (R-PKM) component simultaneously predicting color and depth from fMRI signals. The experiments indicate that our method outperforms the current state-of-the-art models in terms of the consistency of appearance, structure, and semantics. Code will be made publicly available to facilitate further research in this field.
- Open Access
- 26 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Scene Understanding: Do we even need Labels and Data ?
Despite their ever growing sizes, computer vision datasets are doomed to reflect only a tiny fraction of our world. The induced biases raise ethical issues and show that blind reliance on data can have critical outcomes when it comes to applications like autonomous driving. In this talk, we will investigate visual scene understanding in the era of large-scale datasets, self-supervised learning and LLMs. Following our recently published research we will question our use of machine learning and data for real and open world scene understanding by navigating through these questions: Are we making the best use of existing datasets ? Can we benefit from more knowledge priors ? Can vision algorithms perform in the unknown open-world?
- 26 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Open AccessScene Understanding: Do we even need Labels and Data ?
Despite their ever growing sizes, computer vision datasets are doomed to reflect only a tiny fraction of our world. The induced biases raise ethical issues and show that blind reliance on data can have critical outcomes when it comes to applications like autonomous driving. In this talk, we will investigate visual scene understanding in the era of large-scale datasets, self-supervised learning and LLMs. Following our recently published research we will question our use of machine learning and data for real and open world scene understanding by navigating through these questions: Are we making the best use of existing datasets ? Can we benefit from more knowledge priors ? Can vision algorithms perform in the unknown open-world?
- Open Access
Physics-informed Guided Disentanglement in Generative Networks
Image-to-image translation (i2i) networks suffer from entanglement effects in presence of physics-related phenomena in target domain (such as occlusions, fog, etc), lowering altogether the translation quality, controllability and variability. In this paper, we propose a general framework to disentangle visual traits in target images. Primarily, we build upon collection of simple physics models, guiding the disentanglement with a physical model that renders some of the target traits, and learning the remaining ones. Because physics allows explicit and interpretable outputs, our physical models (optimally regressed on target) allows generating unseen scenarios in a controllable manner. Secondarily, we show the versatility of our framework to neural-guided disentanglement where a generative network is used in place of a physical model in case the latter is not directly accessible. Altogether, we introduce three strategies of disentanglement being guided from either a fully differentiable physics model, a (partially) non-differentiable physics model, or a neural network. The results show our disentanglement strategies dramatically increase performances qualitatively and quantitatively in several challenging scenarios for image translation.
Open AccessPhysics-informed Guided Disentanglement in Generative Networks
Image-to-image translation (i2i) networks suffer from entanglement effects in presence of physics-related phenomena in target domain (such as occlusions, fog, etc), lowering altogether the translation quality, controllability and variability. In this paper, we propose a general framework to disentangle visual traits in target images. Primarily, we build upon collection of simple physics models, guiding the disentanglement with a physical model that renders some of the target traits, and learning the remaining ones. Because physics allows explicit and interpretable outputs, our physical models (optimally regressed on target) allows generating unseen scenarios in a controllable manner. Secondarily, we show the versatility of our framework to neural-guided disentanglement where a generative network is used in place of a physical model in case the latter is not directly accessible. Altogether, we introduce three strategies of disentanglement being guided from either a fully differentiable physics model, a (partially) non-differentiable physics model, or a neural network. The results show our disentanglement strategies dramatically increase performances qualitatively and quantitatively in several challenging scenarios for image translation.
- 15 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (8) , 10300-10316
Physics-Informed Guided Disentanglement in Generative Networks
Image-to-image translation (i2i) networks suffer from entanglement effects in presence of physics-related phenomena in target domain (such as occlusions, fog, etc), lowering altogether the translation quality, controllability and variability. In this paper, we propose a general framework to disentangle visual traits in target images. Primarily, we build upon collection of simple physics models, guiding the disentanglement with a physical model that renders some of the target traits, and learning the remaining ones. Because physics allows explicit and interpretable outputs, our physical models (optimally regressed on target) allows generating unseen scenarios in a controllable manner. Secondarily, we show the versatility of our framework to neural-guided disentanglement where a generative network is used in place of a physical model in case the latter is not directly accessible. Altogether, we introduce three strategies of disentanglement being guided from either a fully differentiable physics model, a (partially) non-differentiable physics model, or a neural network. The results show our disentanglement strategies dramatically increase performances qualitatively and quantitatively in several challenging scenarios for image translation.
- 15 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (8) , 10300-10316
Physics-Informed Guided Disentanglement in Generative Networks
Image-to-image translation (i2i) networks suffer from entanglement effects in presence of physics-related phenomena in target domain (such as occlusions, fog, etc), lowering altogether the translation quality, controllability and variability. In this paper, we propose a general framework to disentangle visual traits in target images. Primarily, we build upon collection of simple physics models, guiding the disentanglement with a physical model that renders some of the target traits, and learning the remaining ones. Because physics allows explicit and interpretable outputs, our physical models (optimally regressed on target) allows generating unseen scenarios in a controllable manner. Secondarily, we show the versatility of our framework to neural-guided disentanglement where a generative network is used in place of a physical model in case the latter is not directly accessible. Altogether, we introduce three strategies of disentanglement being guided from either a fully differentiable physics model, a (partially) non-differentiable physics model, or a neural network. The results show our disentanglement strategies dramatically increase performances qualitatively and quantitatively in several challenging scenarios for image translation.
- 24 October 2022
- Published by Springer Nature
- p. 440-456
ManiFest: Manifold Deformation for Few-Shot Image Translation
- 24 October 2022
- Published by Springer Nature
- p. 440-456
ManiFest: Manifold Deformation for Few-Shot Image Translation
- Open Access
COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation
Annotation of large-scale 3D data is notoriously cumbersome and costly. As an alternative, weakly-supervised learning alleviates such a need by reducing the annotation by several order of magnitudes. We propose COARSE3D, a novel architecture-agnostic contrastive learning strategy for 3D segmentation. Since contrastive learning requires rich and diverse examples as keys and anchors, we leverage a prototype memory bank capturing class-wise global dataset information efficiently into a small number of prototypes acting as keys. An entropy-driven sampling technique then allows us to select good pixels from predictions as anchors. Experiments on three projection-based backbones show we outperform baselines on three challenging real-world outdoor datasets, working with as low as 0.001% annotations.
Open AccessCOARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation
Annotation of large-scale 3D data is notoriously cumbersome and costly. As an alternative, weakly-supervised learning alleviates such a need by reducing the annotation by several order of magnitudes. We propose COARSE3D, a novel architecture-agnostic contrastive learning strategy for 3D segmentation. Since contrastive learning requires rich and diverse examples as keys and anchors, we leverage a prototype memory bank capturing class-wise global dataset information efficiently into a small number of prototypes acting as keys. An entropy-driven sampling technique then allows us to select good pixels from predictions as anchors. Experiments on three projection-based backbones show we outperform baselines on three challenging real-world outdoor datasets, working with as low as 0.001% annotations.