Gwanghyun Kim

Aditi, Niket Agarwal, Arslan Ali et al.

We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI -- effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 https://openmdw.ai/license/1-1/ License at https://github.com/nvidia/cosmos}{github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3 . The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3 .

Hoigi Seo, Hayeon Kim, Gwanghyun Kim et al.

The increasing demand for high-quality 3D content creation has motivated the development of automated methods for creating 3D object models from a single image and/or from a text prompt. However, the reconstructed 3D objects using state-of-the-art image-to-3D methods still exhibit low correspondence to the given image and low multi-view consistency. Recent state-of-the-art text-to-3D methods are also limited, yielding 3D samples with low diversity per prompt with long synthesis time. To address these challenges, we propose DITTO-NeRF, a novel pipeline to generate a high-quality 3D NeRF model from a text prompt or a single image. Our DITTO-NeRF consists of constructing high-quality partial 3D object for limited in-boundary (IB) angles using the given or text-generated 2D image from the frontal view and then iteratively reconstructing the remaining 3D NeRF using inpainting latent diffusion model. We propose progressive 3D object reconstruction schemes in terms of scales (low to high resolution), angles (IB angles initially to outer-boundary (OB) later), and masks (object to background boundary) in our DITTO-NeRF so that high-quality information on IB can be propagated into OB. Our DITTO-NeRF outperforms state-of-the-art methods in terms of fidelity and diversity qualitatively and quantitatively with much faster training times than prior arts on image/text-to-3D such as DreamFusion, and NeuralLift-360.

Gwanghyun Kim, Se Young Chun

Recent 3D generative models have achieved remarkable performance in synthesizing high resolution photorealistic images with view consistency and detailed 3D shapes, but training them for diverse domains is challenging since it requires massive training images and their camera distribution information. Text-guided domain adaptation methods have shown impressive performance on converting the 2D generative model on one domain into the models on other domains with different styles by leveraging the CLIP (Contrastive Language-Image Pre-training), rather than collecting massive datasets for those domains. However, one drawback of them is that the sample diversity in the original generative model is not well-preserved in the domain-adapted generative models due to the deterministic nature of the CLIP text encoder. Text-guided domain adaptation will be even more challenging for 3D generative models not only because of catastrophic diversity loss, but also because of inferior text-image correspondence and poor image quality. Here we propose DATID-3D, a domain adaptation method tailored for 3D generative models using text-to-image diffusion models that can synthesize diverse images per text prompt without collecting additional images and camera information for the target domain. Unlike 3D extensions of prior text-guided domain adaptation methods, our novel pipeline was able to fine-tune the state-of-the-art 3D generator of the source domain to synthesize high resolution, multi-view consistent images in text-guided targeted domains without additional data, outperforming the existing text-guided domain adaptation methods in diversity and text-image correspondence. Furthermore, we propose and demonstrate diverse 3D image manipulations such as one-shot instance-selected adaptation and single-view manipulated 3D reconstruction to fully enjoy diversity in text.

Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng et al.

State-of-the-art Vision-Language-Action (VLA) models excel at semantic generalization but struggle to generalize to unseen physical motions in novel environments. We introduce DreamZero, a World Action Model (WAM) built upon a pretrained video diffusion backbone. Unlike VLAs, WAMs learn physical dynamics by predicting future world states and actions, using video as a dense representation of how the world evolves. By jointly modeling video and action, DreamZero learns diverse skills effectively from heterogeneous robot data without relying on repetitive demonstrations. This results in over 2x improvement in generalization to new tasks and environments compared to state-of-the-art VLAs in real robot experiments. Crucially, through model and system optimizations, we enable a 14B autoregressive video diffusion model to perform real-time closed-loop control at 7Hz. Finally, we demonstrate two forms of cross-embodiment transfer: video-only demonstrations from other robots or humans yield a relative improvement of over 42% on unseen task performance with just 10-20 minutes of data. More surprisingly, DreamZero enables few-shot embodiment adaptation, transferring to a new embodiment with only 30 minutes of play data while retaining zero-shot generalization.

Gwanghyun Kim, Ji Ha Jang, Se Young Chun

Recently, significant advancements have been made in 3D generative models, however training these models across diverse domains is challenging and requires an huge amount of training data and knowledge of pose distribution. Text-guided domain adaptation methods have allowed the generator to be adapted to the target domains using text prompts, thereby obviating the need for assembling numerous data. Recently, DATID-3D presents impressive quality of samples in text-guided domain, preserving diversity in text by leveraging text-to-image diffusion. However, adapting 3D generators to domains with significant domain gaps from the source domain still remains challenging due to issues in current text-to-image diffusion models as following: 1) shape-pose trade-off in diffusion-based translation, 2) pose bias, and 3) instance bias in the target domain, resulting in inferior 3D shapes, low text-image correspondence, and low intra-domain diversity in the generated samples. To address these issues, we propose a novel pipeline called PODIA-3D, which uses pose-preserved text-to-image diffusion-based domain adaptation for 3D generative models. We construct a pose-preserved text-to-image diffusion model that allows the use of extremely high-level noise for significant domain changes. We also propose specialized-to-general sampling strategies to improve the details of the generated samples. Moreover, to overcome the instance bias, we introduce a text-guided debiasing method that improves intra-domain diversity. Consequently, our method successfully adapts 3D generators across significant domain gaps. Our qualitative results and user study demonstrates that our approach outperforms existing 3D text-guided domain adaptation methods in terms of text-image correspondence, realism, diversity of rendered images, and sense of depth of 3D shapes in the generated samples

Okchul Jung, Dong Un Kang, Gwanghyun Kim et al.

The world has suffered from COVID-19 (SARS-CoV-2) for the last two years, causing much damage and change in people's daily lives. Thus, automated detection of COVID-19 utilizing deep learning on chest computed tomography (CT) scans became promising, which helps correct diagnosis efficiently. Recently, transformer-based COVID-19 detection method on CT is proposed to utilize 3D information in CT volume. However, its sampling method for selecting slices is not optimal. To leverage rich 3D information in CT volume, we propose a transformer-based COVID-19 detection using a novel data curation and adaptive sampling method using gray level co-occurrence matrices (GLCM). To train the model which consists of CNN layer, followed by transformer architecture, we first executed data curation based on lung segmentation and utilized the entropy of GLCM value of every slice in CT volumes to select important slices for the prediction. The experimental results show that the proposed method improve the detection performance with large margin without much difficult modification to the model.

Gwanghyun Kim, Dong Un Kang, Hoigi Seo et al.

Text-driven large scene image synthesis has made significant progress with diffusion models, but controlling it is challenging. While using additional spatial controls with corresponding texts has improved the controllability of large scene synthesis, it is still challenging to faithfully reflect detailed text descriptions without user-provided controls. Here, we propose DetText2Scene, a novel text-driven large-scale image synthesis with high faithfulness, controllability, and naturalness in a global context for the detailed human-centric text description. Our DetText2Scene consists of 1) hierarchical keypoint-box layout generation from the detailed description by leveraging large language model (LLM), 2) view-wise conditioned joint diffusion process to synthesize a large scene from the given detailed text with LLM-generated grounded keypoint-box layout and 3) pixel perturbation-based pyramidal interpolation to progressively refine the large scene for global coherence. Our DetText2Scene significantly outperforms prior arts in text-to-large scene synthesis qualitatively and quantitatively, demonstrating strong faithfulness with detailed descriptions, superior controllability, and excellent naturalness in a global context.

Gwanghyun Kim, Taesung Kwon, Jong Chul Ye

Recently, GAN inversion methods combined with Contrastive Language-Image Pretraining (CLIP) enables zero-shot image manipulation guided by text prompts. However, their applications to diverse real images are still difficult due to the limited GAN inversion capability. Specifically, these approaches often have difficulties in reconstructing images with novel poses, views, and highly variable contents compared to the training data, altering object identity, or producing unwanted image artifacts. To mitigate these problems and enable faithful manipulation of real images, we propose a novel method, dubbed DiffusionCLIP, that performs text-driven image manipulation using diffusion models. Based on full inversion capability and high-quality image generation power of recent diffusion models, our method performs zero-shot image manipulation successfully even between unseen domains and takes another step towards general application by manipulating images from a widely varying ImageNet dataset. Furthermore, we propose a novel noise combination method that allows straightforward multi-attribute manipulation. Extensive experiments and human evaluation confirmed robust and superior manipulation performance of our methods compared to the existing baselines. Code is available at https://github.com/gwang-kim/DiffusionCLIP.git.

Gwanghyun Kim, Junghun James Kim, Suh Yoon Jeon et al.

Reconstructing textured 3D human models from a single image is fundamental for AR/VR and digital human applications. However, existing methods mostly focus on single individuals and thus fail in multi-human scenes, where naive composition of individual reconstructions often leads to artifacts such as unrealistic overlaps, missing geometry in occluded regions, and distorted interactions. These limitations highlight the need for approaches that incorporate group-level context and interaction priors. We introduce a holistic method that explicitly models both group- and instance-level information. To mitigate perspective-induced geometric distortions, we first transform the input into a canonical orthographic space. Our primary component, Human Group-Instance Multi-View Diffusion (HUG-MVD), then generates complete multi-view normals and images by jointly modeling individuals and group context to resolve occlusions and proximity. Subsequently, the Human Group-Instance Geometric Reconstruction (HUG-GR) module optimizes the geometry by leveraging explicit, physics-based interaction priors to enforce physical plausibility and accurately model inter-human contact. Finally, the multi-view images are fused into a high-fidelity texture. Together, these components form our complete framework, HUG3D. Extensive experiments show that HUG3D significantly outperforms both single-human and existing multi-human methods, producing physically plausible, high-fidelity 3D reconstructions of interacting people from a single image. Project page: https://jongheean11.github.io/HUG3D_project

Gwanghyun Kim, Alonso Martinez, Yu-Chuan Su et al. · cmu

Training diffusion models for audiovisual sequences allows for a range of generation tasks by learning conditional distributions of various input-output combinations of the two modalities. Nevertheless, this strategy often requires training a separate model for each task which is expensive. Here, we propose a novel training approach to effectively learn arbitrary conditional distributions in the audiovisual space.Our key contribution lies in how we parameterize the diffusion timestep in the forward diffusion process. Instead of the standard fixed diffusion timestep, we propose applying variable diffusion timesteps across the temporal dimension and across modalities of the inputs. This formulation offers flexibility to introduce variable noise levels for various portions of the input, hence the term mixture of noise levels. We propose a transformer-based audiovisual latent diffusion model and show that it can be trained in a task-agnostic fashion using our approach to enable a variety of audiovisual generation tasks at inference time. Experiments demonstrate the versatility of our method in tackling cross-modal and multimodal interpolation tasks in the audiovisual space. Notably, our proposed approach surpasses baselines in generating temporally and perceptually consistent samples conditioned on the input. Project page: avdit2024.github.io

Gwanghyun Kim, Hayeon Kim, Hoigi Seo et al.

Generating higher-resolution human-centric scenes with details and controls remains a challenge for existing text-to-image diffusion models. This challenge stems from limited training image size, text encoder capacity (limited tokens), and the inherent difficulty of generating complex scenes involving multiple humans. While current methods attempted to address training size limit only, they often yielded human-centric scenes with severe artifacts. We propose BeyondScene, a novel framework that overcomes prior limitations, generating exquisite higher-resolution (over 8K) human-centric scenes with exceptional text-image correspondence and naturalness using existing pretrained diffusion models. BeyondScene employs a staged and hierarchical approach to initially generate a detailed base image focusing on crucial elements in instance creation for multiple humans and detailed descriptions beyond token limit of diffusion model, and then to seamlessly convert the base image to a higher-resolution output, exceeding training image size and incorporating details aware of text and instances via our novel instance-aware hierarchical enlargement process that consists of our proposed high-frequency injected forward diffusion and adaptive joint diffusion. BeyondScene surpasses existing methods in terms of correspondence with detailed text descriptions and naturalness, paving the way for advanced applications in higher-resolution human-centric scene creation beyond the capacity of pretrained diffusion models without costly retraining. Project page: https://janeyeon.github.io/beyond-scene.

Heechang Kim, Gwanghyun Kim, Se Young Chun

Diverse human motion generation is an increasingly important task, having various applications in computer vision, human-computer interaction and animation. While text-to-motion synthesis using diffusion models has shown success in generating high-quality motions, achieving fine-grained expressive motion control remains a significant challenge. This is due to the lack of motion style diversity in datasets and the difficulty of expressing quantitative characteristics in natural language. Laban movement analysis has been widely used by dance experts to express the details of motion including motion quality as consistent as possible. Inspired by that, this work aims for interpretable and expressive control of human motion generation by seamlessly integrating the quantification methods of Laban Effort and Shape components into the text-guided motion generation models. Our proposed zero-shot, inference-time optimization method guides the motion generation model to have desired Laban Effort and Shape components without any additional motion data by updating the text embedding of pretrained diffusion models during the sampling step. We demonstrate that our approach yields diverse expressive motion qualities while preserving motion identity by successfully manipulating motion attributes according to target Laban tags.

Gwanghyun Kim, Xueting Li, Ye Yuan et al.

Estimating accurate and temporally consistent 3D human geometry from videos is a challenging problem in computer vision. Existing methods, primarily optimized for single images, often suffer from temporal inconsistencies and fail to capture fine-grained dynamic details. To address these limitations, we present GeoMan, a novel architecture designed to produce accurate and temporally consistent depth and normal estimations from monocular human videos. GeoMan addresses two key challenges: the scarcity of high-quality 4D training data and the need for metric depth estimation to accurately model human size. To overcome the first challenge, GeoMan employs an image-based model to estimate depth and normals for the first frame of a video, which then conditions a video diffusion model, reframing video geometry estimation task as an image-to-video generation problem. This design offloads the heavy lifting of geometric estimation to the image model and simplifies the video model's role to focus on intricate details while using priors learned from large-scale video datasets. Consequently, GeoMan improves temporal consistency and generalizability while requiring minimal 4D training data. To address the challenge of accurate human size estimation, we introduce a root-relative depth representation that retains critical human-scale details and is easier to be estimated from monocular inputs, overcoming the limitations of traditional affine-invariant and metric depth representations. GeoMan achieves state-of-the-art performance in both qualitative and quantitative evaluations, demonstrating its effectiveness in overcoming longstanding challenges in 3D human geometry estimation from videos.

Gwanghyun Kim, Suh Yoon Jeon, Seunggyu Lee et al.

We present PersonaCraft, a framework for controllable and occlusion-robust full-body personalized image synthesis of multiple individuals in complex scenes. Current methods struggle with occlusion-heavy scenarios and complete body personalization, as 2D pose conditioning lacks 3D geometry, often leading to ambiguous occlusions and anatomical distortions, and many approaches focus solely on facial identity. In contrast, our PersonaCraft integrates diffusion models with 3D human modeling, employing SMPLx-ControlNet, to utilize 3D geometry like depth and normal maps for robust 3D-aware pose conditioning and enhanced anatomical coherence. To handle fine-grained occlusions, we propose Occlusion Boundary Enhancer Network that exploits depth edge signals with occlusion-focused training, and Occlusion-Aware Classifier-Free Guidance strategy that selectively reinforces conditioning in occluded regions without affecting unoccluded areas. PersonaCraft can seamlessly be combined with Face Identity ControlNet, achieving full-body multi-human personalization and thus marking a significant advancement beyond prior approaches that concentrate only on facial identity. Our dual-pathway body shape representation with SMPLx-based shape parameters and textual refinement, enables precise full-body personalization and flexible user-defined body shape adjustments. Extensive quantitative experiments and user studies demonstrate that PersonaCraft significantly outperforms existing methods in generating high-quality, multi-person images with accurate personalization and robust occlusion handling.

Sangjoon Park, Gwanghyun Kim, Yujin Oh et al.

Although deep learning-based computer-aided diagnosis systems have recently achieved expert-level performance, developing a robust deep learning model requires large, high-quality data with manual annotation, which is expensive to obtain. This situation poses the problem that the chest x-rays collected annually in hospitals cannot be used due to the lack of manual labeling by experts, especially in deprived areas. To address this, here we present a novel deep learning framework that uses knowledge distillation through self-supervised learning and self-training, which shows that the performance of the original model trained with a small number of labels can be gradually improved with more unlabeled data. Experimental results show that the proposed framework maintains impressive robustness against a real-world environment and has general applicability to several diagnostic tasks such as tuberculosis, pneumothorax, and COVID-19. Notably, we demonstrated that our model performs even better than those trained with the same amount of labeled data. The proposed framework has a great potential for medical imaging, where plenty of data is accumulated every year, but ground truth annotations are expensive to obtain.

Sangjoon Park, Gwanghyun Kim, Jeongsol Kim et al.

Federated learning, which shares the weights of the neural network across clients, is gaining attention in the healthcare sector as it enables training on a large corpus of decentralized data while maintaining data privacy. For example, this enables neural network training for COVID-19 diagnosis on chest X-ray (CXR) images without collecting patient CXR data across multiple hospitals. Unfortunately, the exchange of the weights quickly consumes the network bandwidth if highly expressive network architecture is employed. So-called split learning partially solves this problem by dividing a neural network into a client and a server part, so that the client part of the network takes up less extensive computation resources and bandwidth. However, it is not clear how to find the optimal split without sacrificing the overall network performance. To amalgamate these methods and thereby maximize their distinct strengths, here we show that the Vision Transformer, a recently developed deep learning architecture with straightforward decomposable configuration, is ideally suitable for split learning without sacrificing performance. Even under the non-independent and identically distributed data distribution which emulates a real collaboration between hospitals using CXR datasets from multiple sources, the proposed framework was able to attain performance comparable to data-centralized training. In addition, the proposed framework along with heterogeneous multi-task clients also improves individual task performances including the diagnosis of COVID-19, eliminating the need for sharing large weights with innumerable parameters. Our results affirm the suitability of Transformer for collaborative learning in medical imaging and pave the way forward for future real-world implementations.

Sangjoon Park, Gwanghyun Kim, Yujin Oh et al.

Developing a robust algorithm to diagnose and quantify the severity of COVID-19 using Chest X-ray (CXR) requires a large number of well-curated COVID-19 datasets, which is difficult to collect under the global COVID-19 pandemic. On the other hand, CXR data with other findings are abundant. This situation is ideally suited for the Vision Transformer (ViT) architecture, where a lot of unlabeled data can be used through structural modeling by the self-attention mechanism. However, the use of existing ViT is not optimal, since feature embedding through direct patch flattening or ResNet backbone in the standard ViT is not intended for CXR. To address this problem, here we propose a novel Vision Transformer that utilizes low-level CXR feature corpus obtained from a backbone network that extracts common CXR findings. Specifically, the backbone network is first trained with large public datasets to detect common abnormal findings such as consolidation, opacity, edema, etc. Then, the embedded features from the backbone network are used as corpora for a Transformer model for the diagnosis and the severity quantification of COVID-19. We evaluate our model on various external test datasets from totally different institutions to evaluate the generalization capability. The experimental results confirm that our model can achieve the state-of-the-art performance in both diagnosis and severity quantification tasks with superior generalization capability, which are sine qua non of widespread deployment.

Gwanghyun Kim, Sangjoon Park, Yujin Oh et al.

Under the global pandemic of COVID-19, building an automated framework that quantifies the severity of COVID-19 and localizes the relevant lesion on chest X-ray images has become increasingly important. Although pixel-level lesion severity labels, e.g. lesion segmentation, can be the most excellent target to build a robust model, collecting enough data with such labels is difficult due to time and labor-intensive annotation tasks. Instead, array-based severity labeling that assigns integer scores on six subdivisions of lungs can be an alternative choice enabling the quick labeling. Several groups proposed deep learning algorithms that quantify the severity of COVID-19 using the array-based COVID-19 labels and localize the lesions with explainability maps. To further improve the accuracy and interpretability, here we propose a novel Vision Transformer tailored for both quantification of the severity and clinically applicable localization of the COVID-19 related lesions. Our model is trained in a weakly-supervised manner to generate the full probability maps from weak array-based labels. Furthermore, a novel progressive self-training method enables us to build a model with a small labeled dataset. The quantitative and qualitative analysis on the external testset demonstrates that our method shows comparable performance with radiologists for both tasks with stability in a real-world application.

Sangjoon Park, Gwanghyun Kim, Yujin Oh et al.

Under the global COVID-19 crisis, developing robust diagnosis algorithm for COVID-19 using CXR is hampered by the lack of the well-curated COVID-19 data set, although CXR data with other disease are abundant. This situation is suitable for vision transformer architecture that can exploit the abundant unlabeled data using pre-training. However, the direct use of existing vision transformer that uses the corpus generated by the ResNet is not optimal for correct feature embedding. To mitigate this problem, we propose a novel vision Transformer by using the low-level CXR feature corpus that are obtained to extract the abnormal CXR features. Specifically, the backbone network is trained using large public datasets to obtain the abnormal features in routine diagnosis such as consolidation, glass-grass opacity (GGO), etc. Then, the embedded features from the backbone network are used as corpus for vision transformer training. We examine our model on various external test datasets acquired from totally different institutions to assess the generalization ability. Our experiments demonstrate that our method achieved the state-of-art performance and has better generalization capability, which are crucial for a widespread deployment.