Ting-Chun Wang

Niket Agarwal, Arslan Ali, Maciej Bala et al. · nvidia

Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model Platform to help developers build customized world models for their Physical AI setups. We position a world foundation model as a general-purpose world model that can be fine-tuned into customized world models for downstream applications. Our platform covers a video curation pipeline, pre-trained world foundation models, examples of post-training of pre-trained world foundation models, and video tokenizers. To help Physical AI builders solve the most critical problems of our society, we make Cosmos open-source and our models open-weight with permissive licenses available via https://github.com/nvidia-cosmos/cosmos-predict1.

Hassan Abu Alhaija, Jose Alvarez, Maciej Bala et al. · nvidia

We introduce Cosmos-Transfer, a conditional world generation model that can generate world simulations based on multiple spatial control inputs of various modalities such as segmentation, depth, and edge. In the design, the spatial conditional scheme is adaptive and customizable. It allows weighting different conditional inputs differently at different spatial locations. This enables highly controllable world generation and finds use in various world-to-world transfer use cases, including Sim2Real. We conduct extensive evaluations to analyze the proposed model and demonstrate its applications for Physical AI, including robotics Sim2Real and autonomous vehicle data enrichment. We further demonstrate an inference scaling strategy to achieve real-time world generation with an NVIDIA GB200 NVL72 rack. To help accelerate research development in the field, we open-source our models and code at https://github.com/nvidia-cosmos/cosmos-transfer1.

Tim Brooks, Janne Hellsten, Miika Aittala et al. · berkeley, nvidia

We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time while maintaining consistencies expected in real environments, such as plausible dynamics and object persistence. A common failure case is for content to never change due to over-reliance on inductive biases to provide temporal consistency, such as a single latent code that dictates content for the entire video. On the other extreme, without long-term consistency, generated videos may morph unrealistically between different scenes. To address these limitations, we prioritize the time axis by redesigning the temporal latent representation and learning long-term consistency from data by training on longer videos. To this end, we leverage a two-phase training strategy, where we separately train using longer videos at a low resolution and shorter videos at a high resolution. To evaluate the capabilities of our model, we introduce two new benchmark datasets with explicit focus on long-term temporal dynamics.

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 .

Arslan Ali, Junjie Bai, Maciej Bala et al. · nvidia

We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2World, Image2World, and Video2World generation in a single model and leverages [Cosmos-Reason1], a Physical AI vision-language model, to provide richer text grounding and finer control of world simulation. Trained on 200M curated video clips and refined with reinforcement learning-based post-training, [Cosmos-Predict2.5] achieves substantial improvements over [Cosmos-Predict1] in video quality and instruction alignment, with models released at 2B and 14B scales. These capabilities enable more reliable synthetic data generation, policy evaluation, and closed-loop simulation for robotics and autonomous systems. We further extend the family with [Cosmos-Transfer2.5], a control-net style framework for Sim2Real and Real2Real world translation. Despite being 3.5$\times$ smaller than [Cosmos-Transfer1], it delivers higher fidelity and robust long-horizon video generation. Together, these advances establish [Cosmos-Predict2.5] and [Cosmos-Transfer2.5] as versatile tools for scaling embodied intelligence. To accelerate research and deployment in Physical AI, we release source code, pretrained checkpoints, and curated benchmarks under the NVIDIA Open Model License at https://github.com/nvidia-cosmos/cosmos-predict2.5 and https://github.com/nvidia-cosmos/cosmos-transfer2.5. We hope these open resources lower the barrier to adoption and foster innovation in building the next generation of embodied intelligence.

Johanna Karras, Aleksander Holynski, Ting-Chun Wang et al. · uw

We present DreamPose, a diffusion-based method for generating animated fashion videos from still images. Given an image and a sequence of human body poses, our method synthesizes a video containing both human and fabric motion. To achieve this, we transform a pretrained text-to-image model (Stable Diffusion) into a pose-and-image guided video synthesis model, using a novel fine-tuning strategy, a set of architectural changes to support the added conditioning signals, and techniques to encourage temporal consistency. We fine-tune on a collection of fashion videos from the UBC Fashion dataset. We evaluate our method on a variety of clothing styles and poses, and demonstrate that our method produces state-of-the-art results on fashion video animation.Video results are available on our project page.

Yuval Atzmon, Maciej Bala, Yogesh Balaji et al. · nvidia

We introduce Edify Image, a family of diffusion models capable of generating photorealistic image content with pixel-perfect accuracy. Edify Image utilizes cascaded pixel-space diffusion models trained using a novel Laplacian diffusion process, in which image signals at different frequency bands are attenuated at varying rates. Edify Image supports a wide range of applications, including text-to-image synthesis, 4K upsampling, ControlNets, 360 HDR panorama generation, and finetuning for image customization.

Yu-Ying Yeh, Koki Nagano, Sameh Khamis et al.

Given a portrait image of a person and an environment map of the target lighting, portrait relighting aims to re-illuminate the person in the image as if the person appeared in an environment with the target lighting. To achieve high-quality results, recent methods rely on deep learning. An effective approach is to supervise the training of deep neural networks with a high-fidelity dataset of desired input-output pairs, captured with a light stage. However, acquiring such data requires an expensive special capture rig and time-consuming efforts, limiting access to only a few resourceful laboratories. To address the limitation, we propose a new approach that can perform on par with the state-of-the-art (SOTA) relighting methods without requiring a light stage. Our approach is based on the realization that a successful relighting of a portrait image depends on two conditions. First, the method needs to mimic the behaviors of physically-based relighting. Second, the output has to be photorealistic. To meet the first condition, we propose to train the relighting network with training data generated by a virtual light stage that performs physically-based rendering on various 3D synthetic humans under different environment maps. To meet the second condition, we develop a novel synthetic-to-real approach to bring photorealism to the relighting network output. In addition to achieving SOTA results, our approach offers several advantages over the prior methods, including controllable glares on glasses and more temporally-consistent results for relighting videos.

Ting-Chun Wang, Shang-Yu Su, Yun-Nung Chen

Recommendation systems focus on helping users find items of interest in the situations of information overload, where users' preferences are typically estimated by the past observed behaviors. In contrast, conversational recommendation systems (CRS) aim to understand users' preferences via interactions in conversation flows. CRS is a complex problem that consists of two main tasks: (1) recommendation and (2) response generation. Previous work often tried to solve the problem in a modular manner, where recommenders and response generators are separate neural models. Such modular architectures often come with a complicated and unintuitive connection between the modules, leading to inefficient learning and other issues. In this work, we propose a unified framework based on BART for conversational recommendation, which tackles two tasks in a single model. Furthermore, we also design and collect a lightweight knowledge graph for CRS in the movie domain. The experimental results show that the proposed methods achieve the state-of-the-art performance in terms of both automatic and human evaluation.

Siddharth Gururani, Arun Mallya, Ting-Chun Wang et al.

Animating portraits using speech has received growing attention in recent years, with various creative and practical use cases. An ideal generated video should have good lip sync with the audio, natural facial expressions and head motions, and high frame quality. In this work, we present SPACE, which uses speech and a single image to generate high-resolution, and expressive videos with realistic head pose, without requiring a driving video. It uses a multi-stage approach, combining the controllability of facial landmarks with the high-quality synthesis power of a pretrained face generator. SPACE also allows for the control of emotions and their intensities. Our method outperforms prior methods in objective metrics for image quality and facial motions and is strongly preferred by users in pair-wise comparisons. The project website is available at https://deepimagination.cc/SPACE/

Arun Mallya, Ting-Chun Wang, Ming-Yu Liu

We present a new implicit warping framework for image animation using sets of source images through the transfer of the motion of a driving video. A single cross- modal attention layer is used to find correspondences between the source images and the driving image, choose the most appropriate features from different source images, and warp the selected features. This is in contrast to the existing methods that use explicit flow-based warping, which is designed for animation using a single source and does not extend well to multiple sources. The pick-and-choose capability of our framework helps it achieve state-of-the-art results on multiple datasets for image animation using both single and multiple source images. The project website is available at https://deepimagination.cc/implicit warping/

Yu Zeng, Vishal M. Patel, Haochen Wang et al.

Personalized text-to-image generation models enable users to create images that depict their individual possessions in diverse scenes, finding applications in various domains. To achieve the personalization capability, existing methods rely on finetuning a text-to-image foundation model on a user's custom dataset, which can be non-trivial for general users, resource-intensive, and time-consuming. Despite attempts to develop finetuning-free methods, their generation quality is much lower compared to their finetuning counterparts. In this paper, we propose Joint-Image Diffusion (\jedi), an effective technique for learning a finetuning-free personalization model. Our key idea is to learn the joint distribution of multiple related text-image pairs that share a common subject. To facilitate learning, we propose a scalable synthetic dataset generation technique. Once trained, our model enables fast and easy personalization at test time by simply using reference images as input during the sampling process. Our approach does not require any expensive optimization process or additional modules and can faithfully preserve the identity represented by any number of reference images. Experimental results show that our model achieves state-of-the-art generation quality, both quantitatively and qualitatively, significantly outperforming both the prior finetuning-based and finetuning-free personalization baselines.

Taesung Park, Ming-Yu Liu, Ting-Chun Wang et al.

We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the deep network, which is then processed through stacks of convolution, normalization, and nonlinearity layers. We show that this is suboptimal as the normalization layers tend to ``wash away'' semantic information. To address the issue, we propose using the input layout for modulating the activations in normalization layers through a spatially-adaptive, learned transformation. Experiments on several challenging datasets demonstrate the advantage of the proposed method over existing approaches, regarding both visual fidelity and alignment with input layouts. Finally, our model allows user control over both semantic and style. Code is available at https://github.com/NVlabs/SPADE .

Xun Huang, Arun Mallya, Ting-Chun Wang et al.

Existing conditional image synthesis frameworks generate images based on user inputs in a single modality, such as text, segmentation, sketch, or style reference. They are often unable to leverage multimodal user inputs when available, which reduces their practicality. To address this limitation, we propose the Product-of-Experts Generative Adversarial Networks (PoE-GAN) framework, which can synthesize images conditioned on multiple input modalities or any subset of them, even the empty set. PoE-GAN consists of a product-of-experts generator and a multimodal multiscale projection discriminator. Through our carefully designed training scheme, PoE-GAN learns to synthesize images with high quality and diversity. Besides advancing the state of the art in multimodal conditional image synthesis, PoE-GAN also outperforms the best existing unimodal conditional image synthesis approaches when tested in the unimodal setting. The project website is available at https://deepimagination.github.io/PoE-GAN .

Ting-Chun Wang, Arun Mallya, Ming-Yu Liu

We propose a neural talking-head video synthesis model and demonstrate its application to video conferencing. Our model learns to synthesize a talking-head video using a source image containing the target person's appearance and a driving video that dictates the motion in the output. Our motion is encoded based on a novel keypoint representation, where the identity-specific and motion-related information is decomposed unsupervisedly. Extensive experimental validation shows that our model outperforms competing methods on benchmark datasets. Moreover, our compact keypoint representation enables a video conferencing system that achieves the same visual quality as the commercial H.264 standard while only using one-tenth of the bandwidth. Besides, we show our keypoint representation allows the user to rotate the head during synthesis, which is useful for simulating face-to-face video conferencing experiences.

Ming-Yu Liu, Xun Huang, Jiahui Yu et al.

The generative adversarial network (GAN) framework has emerged as a powerful tool for various image and video synthesis tasks, allowing the synthesis of visual content in an unconditional or input-conditional manner. It has enabled the generation of high-resolution photorealistic images and videos, a task that was challenging or impossible with prior methods. It has also led to the creation of many new applications in content creation. In this paper, we provide an overview of GANs with a special focus on algorithms and applications for visual synthesis. We cover several important techniques to stabilize GAN training, which has a reputation for being notoriously difficult. We also discuss its applications to image translation, image processing, video synthesis, and neural rendering.

Arun Mallya, Ting-Chun Wang, Karan Sapra et al.

Video-to-video synthesis (vid2vid) aims for converting high-level semantic inputs to photorealistic videos. While existing vid2vid methods can achieve short-term temporal consistency, they fail to ensure the long-term one. This is because they lack knowledge of the 3D world being rendered and generate each frame only based on the past few frames. To address the limitation, we introduce a novel vid2vid framework that efficiently and effectively utilizes all past generated frames during rendering. This is achieved by condensing the 3D world rendered so far into a physically-grounded estimate of the current frame, which we call the guidance image. We further propose a novel neural network architecture to take advantage of the information stored in the guidance images. Extensive experimental results on several challenging datasets verify the effectiveness of our approach in achieving world consistency - the output video is consistent within the entire rendered 3D world. https://nvlabs.github.io/wc-vid2vid/

Guilin Liu, Rohan Taori, Ting-Chun Wang et al.

Conventional CNNs for texture synthesis consist of a sequence of (de)-convolution and up/down-sampling layers, where each layer operates locally and lacks the ability to capture the long-term structural dependency required by texture synthesis. Thus, they often simply enlarge the input texture, rather than perform reasonable synthesis. As a compromise, many recent methods sacrifice generalizability by training and testing on the same single (or fixed set of) texture image(s), resulting in huge re-training time costs for unseen images. In this work, based on the discovery that the assembling/stitching operation in traditional texture synthesis is analogous to a transposed convolution operation, we propose a novel way of using transposed convolution operation. Specifically, we directly treat the whole encoded feature map of the input texture as transposed convolution filters and the features' self-similarity map, which captures the auto-correlation information, as input to the transposed convolution. Such a design allows our framework, once trained, to be generalizable to perform synthesis of unseen textures with a single forward pass in nearly real-time. Our method achieves state-of-the-art texture synthesis quality based on various metrics. While self-similarity helps preserve the input textures' regular structural patterns, our framework can also take random noise maps for irregular input textures instead of self-similarity maps as transposed convolution inputs. It allows to get more diverse results as well as generate arbitrarily large texture outputs by directly sampling large noise maps in a single pass as well.

Hsin-Ying Lee, Xiaodong Yang, Ming-Yu Liu et al.

Dancing to music is an instinctive move by humans. Learning to model the music-to-dance generation process is, however, a challenging problem. It requires significant efforts to measure the correlation between music and dance as one needs to simultaneously consider multiple aspects, such as style and beat of both music and dance. Additionally, dance is inherently multimodal and various following movements of a pose at any moment are equally likely. In this paper, we propose a synthesis-by-analysis learning framework to generate dance from music. In the analysis phase, we decompose a dance into a series of basic dance units, through which the model learns how to move. In the synthesis phase, the model learns how to compose a dance by organizing multiple basic dancing movements seamlessly according to the input music. Experimental qualitative and quantitative results demonstrate that the proposed method can synthesize realistic, diverse,style-consistent, and beat-matching dances from music.

Ting-Chun Wang, Ming-Yu Liu, Andrew Tao et al.

Video-to-video synthesis (vid2vid) aims at converting an input semantic video, such as videos of human poses or segmentation masks, to an output photorealistic video. While the state-of-the-art of vid2vid has advanced significantly, existing approaches share two major limitations. First, they are data-hungry. Numerous images of a target human subject or a scene are required for training. Second, a learned model has limited generalization capability. A pose-to-human vid2vid model can only synthesize poses of the single person in the training set. It does not generalize to other humans that are not in the training set. To address the limitations, we propose a few-shot vid2vid framework, which learns to synthesize videos of previously unseen subjects or scenes by leveraging few example images of the target at test time. Our model achieves this few-shot generalization capability via a novel network weight generation module utilizing an attention mechanism. We conduct extensive experimental validations with comparisons to strong baselines using several large-scale video datasets including human-dancing videos, talking-head videos, and street-scene videos. The experimental results verify the effectiveness of the proposed framework in addressing the two limitations of existing vid2vid approaches.

Guilin Liu, Kevin J. Shih, Ting-Chun Wang et al.

In this paper, we present a simple yet effective padding scheme that can be used as a drop-in module for existing convolutional neural networks. We call it partial convolution based padding, with the intuition that the padded region can be treated as holes and the original input as non-holes. Specifically, during the convolution operation, the convolution results are re-weighted near image borders based on the ratios between the padded area and the convolution sliding window area. Extensive experiments with various deep network models on ImageNet classification and semantic segmentation demonstrate that the proposed padding scheme consistently outperforms standard zero padding with better accuracy.

Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu et al.

We study the problem of video-to-video synthesis, whose goal is to learn a mapping function from an input source video (e.g., a sequence of semantic segmentation masks) to an output photorealistic video that precisely depicts the content of the source video. While its image counterpart, the image-to-image synthesis problem, is a popular topic, the video-to-video synthesis problem is less explored in the literature. Without understanding temporal dynamics, directly applying existing image synthesis approaches to an input video often results in temporally incoherent videos of low visual quality. In this paper, we propose a novel video-to-video synthesis approach under the generative adversarial learning framework. Through carefully-designed generator and discriminator architectures, coupled with a spatio-temporal adversarial objective, we achieve high-resolution, photorealistic, temporally coherent video results on a diverse set of input formats including segmentation masks, sketches, and poses. Experiments on multiple benchmarks show the advantage of our method compared to strong baselines. In particular, our model is capable of synthesizing 2K resolution videos of street scenes up to 30 seconds long, which significantly advances the state-of-the-art of video synthesis. Finally, we apply our approach to future video prediction, outperforming several state-of-the-art competing systems.

Aysegul Dundar, Ming-Yu Liu, Ting-Chun Wang et al.

Deep neural networks have largely failed to effectively utilize synthetic data when applied to real images due to the covariate shift problem. In this paper, we show that by applying a straightforward modification to an existing photorealistic style transfer algorithm, we achieve state-of-the-art synthetic-to-real domain adaptation results. We conduct extensive experimental validations on four synthetic-to-real tasks for semantic segmentation and object detection, and show that our approach exceeds the performance of any current state-of-the-art GAN-based image translation approach as measured by segmentation and object detection metrics. Furthermore we offer a distance based analysis of our method which shows a dramatic reduction in Frechet Inception distance between the source and target domains, offering a quantitative metric that demonstrates the effectiveness of our algorithm in bridging the synthetic-to-real gap.

Guilin Liu, Fitsum A. Reda, Kevin J. Shih et al.

Existing deep learning based image inpainting methods use a standard convolutional network over the corrupted image, using convolutional filter responses conditioned on both valid pixels as well as the substitute values in the masked holes (typically the mean value). This often leads to artifacts such as color discrepancy and blurriness. Post-processing is usually used to reduce such artifacts, but are expensive and may fail. We propose the use of partial convolutions, where the convolution is masked and renormalized to be conditioned on only valid pixels. We further include a mechanism to automatically generate an updated mask for the next layer as part of the forward pass. Our model outperforms other methods for irregular masks. We show qualitative and quantitative comparisons with other methods to validate our approach.

Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu et al.

We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs). Conditional GANs have enabled a variety of applications, but the results are often limited to low-resolution and still far from realistic. In this work, we generate 2048x1024 visually appealing results with a novel adversarial loss, as well as new multi-scale generator and discriminator architectures. Furthermore, we extend our framework to interactive visual manipulation with two additional features. First, we incorporate object instance segmentation information, which enables object manipulations such as removing/adding objects and changing the object category. Second, we propose a method to generate diverse results given the same input, allowing users to edit the object appearance interactively. Human opinion studies demonstrate that our method significantly outperforms existing methods, advancing both the quality and the resolution of deep image synthesis and editing.

Ting-Chun Wang, Jun-Yan Zhu, Nima Khademi Kalantari et al.

Light field cameras have many advantages over traditional cameras, as they allow the user to change various camera settings after capture. However, capturing light fields requires a huge bandwidth to record the data: a modern light field camera can only take three images per second. This prevents current consumer light field cameras from capturing light field videos. Temporal interpolation at such extreme scale (10x, from 3 fps to 30 fps) is infeasible as too much information will be entirely missing between adjacent frames. Instead, we develop a hybrid imaging system, adding another standard video camera to capture the temporal information. Given a 3 fps light field sequence and a standard 30 fps 2D video, our system can then generate a full light field video at 30 fps. We adopt a learning-based approach, which can be decomposed into two steps: spatio-temporal flow estimation and appearance estimation. The flow estimation propagates the angular information from the light field sequence to the 2D video, so we can warp input images to the target view. The appearance estimation then combines these warped images to output the final pixels. The whole process is trained end-to-end using convolutional neural networks. Experimental results demonstrate that our algorithm outperforms current video interpolation methods, enabling consumer light field videography, and making applications such as refocusing and parallax view generation achievable on videos for the first time.

Nima Khademi Kalantari, Ting-Chun Wang, Ravi Ramamoorthi

With the introduction of consumer light field cameras, light field imaging has recently become widespread. However, there is an inherent trade-off between the angular and spatial resolution, and thus, these cameras often sparsely sample in either spatial or angular domain. In this paper, we use machine learning to mitigate this trade-off. Specifically, we propose a novel learning-based approach to synthesize new views from a sparse set of input views. We build upon existing view synthesis techniques and break down the process into disparity and color estimation components. We use two sequential convolutional neural networks to model these two components and train both networks simultaneously by minimizing the error between the synthesized and ground truth images. We show the performance of our approach using only four corner sub-aperture views from the light fields captured by the Lytro Illum camera. Experimental results show that our approach synthesizes high-quality images that are superior to the state-of-the-art techniques on a variety of challenging real-world scenes. We believe our method could potentially decrease the required angular resolution of consumer light field cameras, which allows their spatial resolution to increase.

Ting-Chun Wang, Jun-Yan Zhu, Ebi Hiroaki et al.

We introduce a new light-field dataset of materials, and take advantage of the recent success of deep learning to perform material recognition on the 4D light-field. Our dataset contains 12 material categories, each with 100 images taken with a Lytro Illum, from which we extract about 30,000 patches in total. To the best of our knowledge, this is the first mid-size dataset for light-field images. Our main goal is to investigate whether the additional information in a light-field (such as multiple sub-aperture views and view-dependent reflectance effects) can aid material recognition. Since recognition networks have not been trained on 4D images before, we propose and compare several novel CNN architectures to train on light-field images. In our experiments, the best performing CNN architecture achieves a 7% boost compared with 2D image classification (70% to 77%). These results constitute important baselines that can spur further research in the use of CNNs for light-field applications. Upon publication, our dataset also enables other novel applications of light-fields, including object detection, image segmentation and view interpolation.