Text-guided diffusion models have revolutionized image and video generation and have also been successfully used for optimization-based 3D object synthesis. Here, we in-stead focus on the underexplored text-to-4D setting and syn-thesize dynamic, animated 3D objects using score distillation methods with an additional temporal dimension. compared to previous work, we pursue a novel compositional generation-based approach, and combine text-to-image, text-to-video, and 3D-aware multiview diffusion models to provide feedback during 4D object optimization, thereby si-multaneously enforcing temporal consistency, high-quality visual appearance and realistic geometry. Our method, called Align Your Gaussians (A YG), leverages dynamic 3D Gaussian Splatting with deformation fields as 4D represen-tation. Crucial to AYG is a novel method to regularize the distribution of the moving 3D Gaussians and thereby sta-bilize the optimization and induce motion. We also pro-pose a motion amplification mechanism as well as a new autoregressive synthesis scheme to generate and combine multiple 4D sequences for longer generation. These techniques allow us to synthesize vivid dynamic scenes, out-perform previous work qualitatively and quantitatively and achieve state-of-the-art text-to-4D performance. Due to the Gaussian 4D representation, different 4D animations can be seamlessly combined, as we demonstrate. AYG opens up promising avenues for animation, simulation and digital content creation as well as synthetic data generation.

Diffusion models have recently received increasing research attention for their remarkable transfer abilities in semantic segmentation tasks. However, generating fine-grained segmentation masks with diffusion models often requires additional training on annotated datasets, leaving it unclear to what extent pre-trained diffusion models alone understand the semantic relations of their generated images. To address this question, we leverage the semantic knowledge extracted from Stable Diffusion (SD) and aim to develop an image segmentor capable of generating fine-grained segmentation maps without any additional training. The primary difficulty stems from the fact that semantically meaningful feature maps typically exist only in the spatially lower-dimensional layers, which poses a challenge in directly extracting pixel-level semantic relations from these feature maps. To overcome this issue, our framework identifies semantic correspondences between image pixels and spatial locations of low-dimensional feature maps by exploiting SD's generation process and utilizes them for constructing image-resolution segmentation maps. In extensive experiments, the produced segmentation maps are demonstrated to be well delineated and capture detailed parts of the images, indicating the existence of highly accurate pixel-level semantic knowledge in diffusion models. Project page: https://kmcode1.github.io/Projects/EmerDiff/

Modern learning-based approaches to 3D-aware image synthesis achieve high photorealism and 3D-consistent viewpoint changes for the generated images. Existing approaches represent instances in a shared canonical space. However, for in-the-wild datasets a shared canonical system can be difficult to define or might not even exist. In this work, we instead model instances in view space, alleviating the need for posed images and learned camera distributions. We find that in this setting, existing GAN-based methods are prone to generating flat geometry and struggle with distribution coverage. We hence propose WildFusion, a new approach to 3D-aware image synthesis based on latent diffusion models (LDMs). We first train an autoencoder that infers a compressed latent representation, which additionally captures the images’ underlying 3D structure and enables not only reconstruction but also novel view synthesis. To learn a faithful 3D representation, we leverage cues from monocular depth prediction. Then, we train a diffusion model in the 3D-aware latent space, thereby enabling synthesis of high-quality 3D-consistent image samples, outperforming recent state-of-the-art GAN-based methods. Importantly, our 3D-aware LDM is trained without any direct supervision from multiview images or 3D geometry and does not require posed images or learned pose or camera distributions. It directly learns a 3D representation without relying on canonical camera coordinates. This opens up promising research avenues for scalable 3D-aware image synthesis and 3D content creation from in-the-wild image data.

We present EmerNeRF, a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. Grounded in neural fields, EmerNeRF simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping. EmerNeRF hinges upon two core components: First, it stratifies scenes into static and dynamic fields. This decomposition emerges purely from self-supervision, enabling our model to learn from general, in-the-wild data sources. Second, EmerNeRF parameterizes an induced flow field from the dynamic field and uses this flow field to further aggregate multi-frame features, amplifying the rendering precision of dynamic objects. Coupling these three fields (static, dynamic, and flow) enables EmerNeRF to represent highly-dynamic scenes self-sufficiently, without relying on ground truth object annotations or pre-trained models for dynamic object segmentation or optical flow estimation. Our method achieves state-of-the-art performance in sensor simulation, significantly outperforming previous methods when reconstructing static (+2.93 PSNR) and dynamic (+3.70 PSNR) scenes. In addition, to bolster EmerNeRF's semantic generalization, we lift 2D visual foundation model features into 4D space-time and address a general positional bias in modern Transformers, significantly boosting 3D perception performance (e.g., 37.50% relative improvement in occupancy prediction accuracy on average). Finally, we construct a diverse and challenging 120-sequence dataset to benchmark neural fields under extreme and highly-dynamic settings. See the project page for code, data, and request pre-trained models: https://emernerf.github.io

We present L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only a second. Key to our success is a novel dataset of multiview videos containing curated, rendered animated objects from Objaverse. This dataset depicts 44K diverse objects with 110K animations rendered in 48 viewpoints, resulting in 12M videos with a total of 300M frames. We keep our L4GM simple for scalability and build directly on top of LGM, a pretrained 3D Large Reconstruction Model that outputs 3D Gaussian ellipsoids from multiview image input. L4GM outputs a per-frame 3D Gaussian splat representation from video frames sampled at a low fps and then upsamples the representation to a higher fps to achieve temporal smoothness. We add temporal self-attention layers to the base LGM to help it learn consistency across time, and utilize a per-timestep multiview rendering loss to train the model. The representation is upsampled to a higher framerate by training an interpolation model which produces intermediate 3D Gaussian representations. We showcase that L4GM that is only trained on synthetic data generalizes well on in-the-wild videos, producing high quality animated 3D assets.

We propose DistillNeRF, a self-supervised learning framework addressing the challenge of understanding 3D environments from limited 2D observations in outdoor autonomous driving scenes. Our method is a generalizable feedforward model that predicts a rich neural scene representation from sparse, single-frame multi-view camera inputs with limited view overlap, and is trained self-supervised with differentiable rendering to reconstruct RGB, depth, or feature images. Our first insight is to exploit per-scene optimized Neural Radiance Fields (NeRFs) by generating dense depth and virtual camera targets from them, which helps our model to learn enhanced 3D geometry from sparse non-overlapping image inputs. Second, to learn a semantically rich 3D representation, we propose distilling features from pre-trained 2D foundation models, such as CLIP or DINOv2, thereby enabling various downstream tasks without the need for costly 3D human annotations. To leverage these two insights, we introduce a novel model architecture with a two-stage lift-splat-shoot encoder and a parameterized sparse hierarchical voxel representation. Experimental results on the NuScenes and Waymo NOTR datasets demonstrate that DistillNeRF significantly outperforms existing comparable state-of-the-art self-supervised methods for scene reconstruction, novel view synthesis, and depth estimation; and it allows for competitive zero-shot 3D semantic occupancy prediction, as well as open-world scene understanding through distilled foundation model features. Demos and code will be available at https://distillnerf.github.io/.

Automatically generating high-quality real world 3D scenes is of enormous interest for applications such as virtual reality and robotics simulation. Towards this goal, we introduce NeuralField-LDM, a generative model capable of synthesizing complex 3D environments. We leverage Latent Diffusion Models that have been successfully utilized for efficient high-quality 2D content creation. We first train a scene auto-encoder to express a set of image and pose pairs as a neural field, represented as density and feature voxel grids that can be projected to produce novel views of the scene. To further compress this representation, we train a latent-autoencoder that maps the voxel grids to a set of latent representations. A hierarchical diffusion model is then fit to the latents to complete the scene generation pipeline. We achieve a substantial improvement over existing state-of-the-art scene generation models. Additionally, we show how NeuralField-LDM can be used for a variety of 3D content creation applications, including conditional scene generation, scene inpainting and scene style manipulation.

Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution video generation, a particularly resource-intensive task. We first pre-train an LDM on images only; then, we turn the image generator into a video generator by introducing a temporal dimension to the latent space diffusion model and finetuning on encoded image sequences, i.e., videos. Similarly, we temporally align diffusion model upsamplers, turning them into temporally consistent video super resolution models. We focus on two relevant real-world applications: Simulation of in-the-wild driving data and creative content creation with text-to-video modeling. In particular, we validate our Video LDM on real driving videos of resolution$512 \times 1024$, achieving state-of-the-art performance. Furthermore, our approach can easily leverage off-the-shelf pretrained image LDMs, as we only need to train a temporal alignment model in that case. Doing so, we turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to$1280 \times 2048$. We show that the temporal layers trained in this way generalize to different finetuned text-to-image LDMs. Utilizing this property, we show the first results for personalized text-to-video generation, opening exciting directions for future content creation. Project page: https://nv-tlabs.github.io/VideoLDM/

In this work, we introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones. We propose to distill knowledge from a trained generative model into standard image backbones that have been well engineered for specific perception tasks. We investigate two types of knowledge distillation: 1) distilling learned generative features onto target image backbones as an alternative to pretraining these backbones on large labeled datasets such as ImageNet, and 2) distilling labels obtained from generative networks with task heads onto logits of target backbones. We perform extensive analyses on multiple generative models, dense prediction benchmarks, and several pre-training regimes. We empirically find that our DreamTeacher significantly outperforms existing self-supervised representation learning approaches across the board. Unsupervised ImageNet pre-training with DreamTeacher leads to significant improvements over ImageNet classification pre-training on downstream datasets, showcasing generative models, and diffusion generative models specifically, as a promising approach to representation learning on large, diverse datasets without requiring manual annotation.

Modern image generative models show remarkable sample quality when trained on a single domain or class of objects. In this work, we introduce a generative adversarial network that can simultaneously generate aligned image samples from multiple related domains. We leverage the fact that a variety of object classes share common attributes, with certain geometric differences. We propose Polymorphic-GAN which learns shared features across all domains and a per-domain morph layer to morph shared features according to each domain. In contrast to previous works, our framework allows simultaneous modelling of images with highly varying geometries, such as images of human faces, painted and artistic faces, as well as multiple different animal faces. We demonstrate that our model produces aligned samples for all domains and show how it can be used for applications such as segmentation transfer and cross-domain image editing, as well as training in low-data regimes. Additionally, we apply our Polymorphic-GAN on image-to-image translation tasks and show that we can greatly surpass previous approaches in cases where the geometric differences between domains are large.

Annotating images with pixel-wise labels is a time consuming and costly process. Recently, DatasetGAN [78] showcased a promising alternative - to synthesize a large labeled dataset via a generative adversarial network (GAN) by exploiting a small set of manually labeled, GAN generated images. Here, we scale DatasetGAN to ImageNet scale of class diversity. We take image samples from the class-conditional generative model BigGAN [5] trained on ImageNet, and manually annotate only 5 images per class, for all 1k classes. By training an effective feature segmentation architecture on top of BigGAN, we turn Big GAN into a labeled dataset generator. We further show that VQGAN [18] can similarly serve as a dataset generator, leveraging the already annotated data. We create a new ImageNet benchmark by labeling an additional set of real images and evaluate segmentation performance in a variety of settings. Through an extensive ablation study, we show big gains in leveraging a large generated dataset to train different supervised and self-supervised backbone models on pixel-wise tasks. Furthermore, we demonstrate that using our synthesized datasets for pre-training leads to improvements over standard ImageNet pre-training on several downstream datasets, such as PASCAL-VOC, MS-COCO, Cityscapes and chest X-ray, as well as tasks (detection, segmentation). Our benchmark will be made public and maintain a leaderboard for this challenging task. Project Page: https://nv-tlabs.github.io/big-datasetgan/

Realistic simulators are critical for training and verifying robotics systems. While most of the contemporary simulators are hand-crafted, a scaleable way to build simulators is to use machine learning to learn how the environment behaves in response to an action, directly from data. In this work, we aim to learn to simulate a dynamic environment directly in pixel-space, by watching unannotated sequences of frames and their associated actions. We introduce a novel high-quality neural simulator referred to as DriveGAN that achieves controllability by disentangling different components without supervision. In addition to steering controls, it also includes controls for sampling features of a scene, such as the weather as well as the location of non-player objects. Since DriveGAN is a fully differentiable simulator, it further allows for re-simulation of a given video sequence, offering an agent to drive through a recorded scene again, possibly taking different actions. We train DriveGAN on multiple datasets, including 160 hours of real-world driving data. We showcase that our approach greatly surpasses the performance of previous data-driven simulators, and al-lows for new key features not explored before.

Generative adversarial networks (GANs) have recently found applications in image editing. However, most GAN-based image editing methods often require large-scale datasets with semantic segmentation annotations for training, only provide high-level control, or merely interpolate between different images. Here, we propose EditGAN, a novel method for high-quality, high-precision semantic image editing, allowing users to edit images by modifying their highly detailed part segmentation masks, e.g., drawing a new mask for the headlight of a car. EditGAN builds on a GAN framework that jointly models images and their semantic segmentation, requiring only a handful of labeled examples – making it a scalable tool for editing. Specifically, we embed an image into the GAN’s latent space and perform conditional latent code optimization according to the segmentation edit, which effectively also modifies the image. To amortize optimization, we find “editing vectors” in latent space that realize the edits. The framework allows us to learn an arbitrary number of editing vectors, which can then be directly applied on other images at interactive rates. We experimentally show that EditGAN can manipulate images with an unprecedented level of detail and freedom while preserving full image quality. We can also easily combine multiple edits and perform plausible edits beyond EditGAN’s training data. We demonstrate EditGAN on a wide variety of image types and quantitatively outperform several previous editing methods on standard editing benchmark tasks.

Simulation is a crucial component of any robotic system. In order to simulate correctly, we need to write complex rules of the environment: how dynamic agents behave, and how the actions of each of the agents affect the behavior of others. In this paper, we aim to learn a simulator by simply watching an agent interact with an environment. We focus on graphics games as a proxy of the real environment. We introduce GameGAN, a generative model that learns to visually imitate a desired game by ingesting screenplay and keyboard actions during training. Given a key pressed by the agent, GameGAN "renders" the next screen using a carefully designed generative adversarial network. Our approach offers key advantages over existing work: we design a memory module that builds an internal map of the environment, allowing for the agent to return to previously visited locations with high visual consistency. In addition, GameGAN is able to disentangle static and dynamic components within an image making the behavior of the model more interpretable, and relevant for downstream tasks that require explicit reasoning over dynamic elements. This enables many interesting applications such as swapping different components of the game to build new games that do not exist. We will release the code and trained model, enabling human players to play generated games and their variations with our GameGAN.

In images of complex scenes, objects are often occluding each other which makes perception tasks such as object detection and tracking, or robotic control tasks such as planning, challenging. To facilitate downstream tasks, it is thus important to reason about the full extent of objects, i.e., seeing behind occlusion, typically referred to as amodal instance completion. In this paper, we propose a variational generative framework for amodal completion, referred to as AMODAL-VAE, which does not require any amodal labels at training time, as it is able to utilize widely available object instance masks. We showcase our approach on the downstream task of scene editing where the user is presented with interactive tools to complete and erase objects in photographs. Experiments on complex street scenes demonstrate state-of-the-art performance in amodal mask completion and showcase high-quality scene editing results. Interestingly, a user study shows that humans prefer object completions inferred by our model to the human-labeled ones.