Abstract The scalability of ambient sound generators is hindered by data scarcity, insufficient caption quality, and limited scalability in model architecture. This work addresses these challenges by advancing both data and model scaling. First, we propose an efficient and scalable dataset collection pipeline tailored for ambient audio generation, resulting in AutoReCap-XL, the largest ambient audio-text dataset with over 47 million clips. To provide high-quality textual annotations, we propose AutoCap, a high-quality automatic audio captioning model. By adopting a Q-Former module and leveraging audio metadata, AutoCap substantially enhances caption quality, reaching a CIDEr score of 83.2, a $$3.2\%$$ 3.2 % improvement over previous captioning models. Finally, we propose GenAu, a scalable transformer-based audio generation architecture that we scale up to 1.25B parameters. We demonstrate its benefits from data scaling with synthetic captions as well as model size scaling. When compared to baseline audio generators trained at similar size and data scale , GenAu obtains significant improvements of $$4.7\%$$ 4.7 % in FAD score, $$22.65\%$$ 22.65 % in IS, and $$13.5\%$$ 13.5 % in CLAP score. Our code, model checkpoints, and dataset are publicly available .

We propose 4Real-Video, a novel framework for generating 4D videos, organized as a grid of video frames with both time and viewpoint axes. In this grid, each row contains frames sharing the same timestep, while each column contains frames from the same viewpoint. We propose a novel two-stream architecture. One stream performs viewpoint updates on columns, and the other stream performs temporal updates on rows. After each diffusion transformer layer, a synchronization layer exchanges information between the two token streams. We propose two implementations of the synchronization layer, using either hard or soft synchronization. This feedforward architecture improves upon previous work in three ways: higher inference speed, enhanced visual quality (measured by FVD, CLIP, and VideoScore), and improved temporal and viewpoint consistency (measured by VideoScore and Dust3R-Confidence).

Numerous works have recently integrated 3D camera control into foundational text-to-video models, but the resulting camera control is often imprecise, and video generation quality suffers. In this work, we analyze camera motion from a first principles perspective, uncovering insights that enable precise 3D camera manipulation without compromising synthesis quality. First, we determine that motion induced by camera movements in videos is low-frequency in nature. This motivates us to adjust train and test pose conditioning schedules, accelerating training convergence while improving visual and motion quality. Then, by probing the representations of an unconditional video diffusion transformer, we observe that they implicitly perform camera pose estimation under the hood, and only a sub-portion of their layers contain the camera information. This suggested us to limit the injection of camera conditioning to a subset of the architecture to prevent interference with other video features, leading to a 4× reduction of training parameters, improved training speed, and 10% higher visual quality. Finally, we complement the typical dataset for camera control learning with a curated dataset of 20K diverse, dynamic videos with stationary cameras. This helps the model distinguish between camera and scene motion and improves the dynamics of generated pose-conditioned videos. We compound these findings to design the Advanced 3D Camera Control (AC3D) architecture, the new state-of-the-art model for generative video modeling with camera control.

Video personalization methods allow us to synthesize videos with specific concepts such as people, pets, and places. However, existing methods often focus on limited domains, require time-consuming optimization per subject, or support only a single subject. We present Video Alchemist—a video model with built-in multi-subject, openset personalization capabilities for both foreground objects and background, eliminating the need for time-consuming test-time optimization. Our model is built on a new Diffusion Transformer module that fuses each conditional reference image and its corresponding subject-level text prompt with cross-attention layers. Developing such a large model presents two main challenges: dataset and evaluation. First, as paired datasets of reference images and videos are extremely hard to collect, we sample selected video frames as reference images and synthesize a clip of the target video. However, while models can easily denoise training videos given reference frames, they fail to generalize to new contexts. To mitigate this issue, we design a new automatic data construction pipeline with extensive image augmentations. Second, evaluating open-set video personalization is a challenge in itself. To address this, we introduce a personalization benchmark that focuses on accurate subject fidelity and supports diverse personalization scenarios. Finally, our extensive experiments show that our method significantly outperforms existing personalization methods in both quantitative and qualitative evaluations.

We propose DiTFlow, a method for transferring the motion of a reference video to a newly synthesized one, designed specifically for Diffusion Transformers (DiT). We first process the reference video with a pre-trained DiT to analyze cross-frame attention maps and extract a patch-wise motion signal called the Attention Motion Flow (AMF). We guide the latent denoising process in an optimization-based, training-free, manner by optimizing latents with our AMF loss to generate videos reproducing the motion of the reference one. We also apply our optimization strategy to transformer positional embeddings, granting us a boost in zero-shot motion transfer capabilities. We evaluate DiTFlow against recently published methods, outperforming all across multiple metrics and human evaluation.

Real-world videos consist of sequences of events. Generating such sequences with precise temporal control is infeasible with existing video generators that rely on a single paragraph of text as input. When tasked with generating multiple events described using a single prompt, such methods often ignore some of the events or fail to arrange them in the correct order. To address this limitation, we present MinT, a multi-event video generator with temporal control. Our key insight is to bind each event to a specific period in the generated video, which allows the model to focus on one event at a time. To enable time-aware interactions between event captions and video tokens, we design a time-based positional encoding method, dubbed ReRoPE. This encoding helps to guide the cross-attention operation. By fine-tuning a pre-trained video diffusion transformer on temporally grounded data, our approach produces coherent videos with smoothly connected events. For the first time in the literature, our model offers control over the timing of events in generated videos. Extensive experiments demonstrate that MinT outperforms existing commercial and open-source models by a large margin. Additional results and details are available at our project page.

We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our framework is a Fusion Block that facilitates bidirectional information exchange between video and audio diffusion models through temporally-aligned self attention operations. Unlike prior work that uses dedicated models for A2V and V2A tasks and relies on pretrained feature extractors, AV-Link achieves both tasks in a single self-contained framework, directly leveraging features obtained by the complementary modality (i.e. video features to generate audio, or audio features to generate video). Extensive automatic and subjective evaluations demonstrate that our method achieves a substantial improvement in audio-video synchronization, outperforming more expensive baselines such as the MovieGen video-to-audio model.

Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of complex videos from a text description. However, most existing models lack fine-grained control over camera movement, which is critical for downstream applications related to content creation, visual effects, and 3D vision. Recently, new methods demonstrate the ability to generate videos with controllable camera poses---these techniques leverage pre-trained U-Net-based diffusion models that explicitly disentangle spatial and temporal generation. Still, no existing approach enables camera control for new, transformer-based video diffusion models that process spatial and temporal information jointly. Here, we propose to tame video transformers for 3D camera control using a ControlNet-like conditioning mechanism that incorporates spatiotemporal camera embeddings based on Plucker coordinates. The approach demonstrates state-of-the-art performance for controllable video generation after fine-tuning on the RealEstate10K dataset. To the best of our knowledge, our work is the first to enable camera control for transformer-based video diffusion models.

We propose a novel approach for 3D mesh reconstruction from multi-view images. We improve upon the large reconstruction model LRM that use a transformer-based triplane generator and a Neural Radiance Field (NeRF) model trained on multi-view images. We introduce three key components to significantly enhance the 3D reconstruction quality. First of all, we examine the original LRM architecture and find several shortcomings. Subsequently, we introduce respective modifications to the LRM architecture, which lead to improved multi-view image representation and more computationally efficient training. Second, in order to improve geometry reconstruction and enable supervision at full image resolution, we extract meshes from the NeRF in a differentiable manner and fine-tune the NeRF model through mesh rendering. These modifications allow us to achieve state-of-the-art performance on both 2D and 3D evaluation metrics on Google Scanned Objects (GSO) dataset and OmniObject3D dataset. Finally, we introduce a lightweight per-instance texture refinement procedure to better reconstruct complex textures, such as text and portraits on assets. To address this, we introduce a lightweight per-instance texture refinement procedure. This procedure fine-tunes the triplane representation and the NeRF's color estimation model on the mesh surface using the input multi-view images in just 4 seconds. This refinement achieves faithful reconstruction of complex textures. Additionally, our approach enables various downstream applications, including text/image-to-3D generation.

Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements have primarily focused on scaling diffusion backbones and improving autoencoder reconstruction quality, the interaction between these components has received comparatively less attention. In this work, we perform a spectral analysis of modern autoencoders and identify inordinate high-frequency components in their latent spaces, which are especially pronounced in the autoencoders with a large bottleneck channel size. We hypothesize that this high-frequency component interferes with the coarse-to-fine nature of the diffusion synthesis process and hinders the generation quality. To mitigate the issue, we propose scale equivariance: a simple regularization strategy that aligns latent and RGB spaces across frequencies by enforcing scale equivariance in the decoder. It requires minimal code changes and only up to $20$K autoencoder fine-tuning steps, yet significantly improves generation quality, reducing FID by 19% for image generation on ImageNet-1K 256x256 and FVD by at least 44% for video generation on Kinetics-700 17x256x256. The source code is available at https://github.com/snap-research/diffusability.

Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fine spectral autoregressive manner. While diffusion models benefit from the coarse-to-fine nature of denoising, explicit multi-stage architectures are rarely adopted. These architectures have increased the complexity of the overall approach, introducing the need for a custom diffusion formulation, decomposition-dependent stage transitions, ad-hoc samplers, or a model cascade. Our contribution, Decomposable Flow Matching (DFM), is a simple and effective framework for the progressive generation of visual media. DFM applies Flow Matching independently at each level of a user-defined multi-scale representation (such as Laplacian pyramid). As shown by our experiments, our approach improves visual quality for both images and videos, featuring superior results compared to prior multistage frameworks. On Imagenet-1k 512px, DFM achieves 35.2% improvements in Frechet DINOv2 Distance (FDD) scores over the base architecture and 26.4% over the best-performing baseline, under the same training compute. When applied to finetuning of large models, such as FLUX, DFM shows faster convergence speed to the training distribution. Crucially, all these advantages are achieved with a single model, architectural simplicity, and minimal modifications to existing training pipelines.

We propose the first framework capable of computing a 4D spatio-temporal grid of video frames and 3D Gaussian particles for each time step using a feed-forward architecture. Our architecture has two main components, a 4D video model and a 4D reconstruction model. In the first part, we analyze current 4D video diffusion architectures that perform spatial and temporal attention either sequentially or in parallel within a two-stream design. We highlight the limitations of existing approaches and introduce a novel fused architecture that performs spatial and temporal attention within a single layer. The key to our method is a sparse attention pattern, where tokens attend to others in the same frame, at the same timestamp, or from the same viewpoint. In the second part, we extend existing 3D reconstruction algorithms by introducing a Gaussian head, a camera token replacement algorithm, and additional dynamic layers and training. Overall, we establish a new state of the art for 4D generation, improving both visual quality and reconstruction capability.

Direct Preference Optimization (DPO) has recently been applied as a post‑training technique for text-to-video diffusion models. To obtain training data, annotators are asked to provide preferences between two videos generated from independent noise. However, this approach prohibits fine-grained comparisons, and we point out that it biases the annotators towards low-motion clips as they often contain fewer visual artifacts. In this work, we introduce DenseDPO, a method that addresses these shortcomings by making three contributions. First, we create each video pair for DPO by denoising corrupted copies of a ground truth video. This results in aligned pairs with similar motion structures while differing in local details, effectively neutralizing the motion bias. Second, we leverage the resulting temporal alignment to label preferences on short segments rather than entire clips, yielding a denser and more precise learning signal. With only one‑third of the labeled data, DenseDPO greatly improves motion generation over vanilla DPO, while matching it in text alignment, visual quality, and temporal consistency. Finally, we show that DenseDPO unlocks automatic preference annotation using off-the-shelf Vision Language Models (VLMs): GPT accurately predicts segment-level preferences similar to task-specifically fine-tuned video reward models, and DenseDPO trained on these labels achieves performance close to using human labels.

Recent advances in text-to-video generation have enabled high-quality synthesis from text and image prompts. While the personalization of dynamic concepts, which capture subject-specific appearance and motion from a single video, is now feasible, most existing methods require per-instance fine-tuning, limiting scalability. We introduce a fully zero-shot framework for dynamic concept personalization in text-to-video models. Our method leverages structured 2×2 video grids that spatially organize input and output pairs, enabling the training of lightweight Grid-LoRA adapters for editing and composition within these grids. At inference, a dedicated Grid Fill module completes partially observed layouts, producing temporally coherent and identity preserving outputs. Once trained, the entire system operates in a single forward pass, generalizing to previously unseen dynamic concepts without any test-time optimization. Extensive experiments demonstrate high-quality and consistent results across a wide range of subjects beyond trained concepts and editing scenarios.

The quality of the data and annotation upper-bounds the quality of a downstream model. While there exist large text corpora and image-text pairs, high-quality video-text data is much harder to collect. First of all, manual labeling is more time-consuming, as it requires an annotator to watch an entire video. Second, videos have a temporal dimension, consisting of several scenes stacked together, and showing multiple actions. Accordingly, to establish a video dataset with high-quality captions, we propose an automatic approach leveraging multimodal inputs, such as textual video description, subtitles, and individual video frames. Specifically, we curate 3.8M high-resolution videos from the publicly available HD-VILA-100M dataset. We then split them into semantically consistent video clips, and apply multiple cross-modality teacher models to obtain captions for each video. Next, we finetune a retrieval model on a small subset where the best caption of each video is manually selected and then employ the model in the whole dataset to select the best caption as the annotation. In this way, we get 70M videos paired with high-quality text captions. We dub the dataset as Panda-70M. We show the value of the proposed dataset on three downstream tasks: video captioning, video and text retrieval, and text-driven video generation. The models trained on the proposed data score substantially better on the majority of metrics across all the tasks.

We present SPAD, a novel approach for creating con-sistent multi-view images from text prompts or single images. To enable multi-view generation, we repurpose a pre-trained 2D diffusion model by extending its self-attention layers with cross-view interactions, and fine-tune it on a high quality subset of Objaverse. We find that a naive extension of the self-attention proposed in prior work (e.g., MV-Dream) leads to content copying between views. Therefore, we explicitly constrain the cross-view attention based on epipolar geometry. To further enhance 3D consistency, we utilize Plücker coordinates derived from camera rays and inject them as positional encoding. This enables SPAD to reason over spatial proximity in 3D well. Compared to concurrent works that can only generate views at fixed azimuth and elevation (e.g., MVDream, SyncDreamer), SPAD offers full camera control and achieves state-of-the-art results in novel view synthesis on unseen objects from the Objaverse and Google Scanned Objects datasets. Finally, we demon-strate that text-to-3D generation using SPAD prevents the multi-face Janus issue.

Contemporary models for generating images show remarkable quality and versatility. Swayed by these advantages, the research community repurposes them to generate videos. Since video content is highly redundant, we argue that naively bringing advances of image models to the video generation domain reduces motion fidelity, visual quality and impairs scalability. In this work, we build Snap Video, a video-first model that systematically addresses these challenges. To do that, we first extend the EDM framework to take into account spatially and temporally redundant pixels and naturally support video generation. Second, we show that a U-Net—a workhorse behind image generation—scales poorly when generating videos, requiring significant computational overhead. Hence, we propose a new transformer-based architecture that trains 3.31 times faster than U-Nets (and is ∼4.5 faster at inference). This allows us to efficiently train a text-to-video model with billions of parameters for the first time, reach state-of-the-art results on a number of benchmarks, and generate videos with substantially higher quality, temporal consistency, and motion complexity. The user studies showed that our model was favored by a large margin over the most recent methods.

Diffusion models have demonstrated remarkable performance in image and video synthesis. However, scaling them to high-resolution inputs is challenging and requires restructuring the diffusion pipeline into multiple independent components, limiting scalability and complicating down-stream applications. In this work, we study patch diffusion models (PDMs) — a diffusion paradigm which models the distribution of patches, rather than whole inputs, keeping up to ≈0.7% of the original pixels. This makes it very efficient during training and unlocks end-to-end optimization on high-resolution videos. We improve PDMs in two principled ways. First, to enforce consistency between patches, we develop deep context fusion — an architectural technique that propagates the context information from low-scale to high-scale patches in a hierarchical manner. Second, to accelerate training and inference, we propose adaptive computation, which allocates more network capacity and computation towards coarse image details. The resulting model sets a new state-of-the-art FVD score of 66.32 and Inception Score of 87.68 in class-conditional video generation on UCF-101 2562, surpassing recent methods by more than 100%. Then, we show that it can be rapidly fine-tuned from a base$36\times 64$low-resolution generator for high-resolution$64\times 288\times 512$text-to-video synthesis. To the best of our knowledge, our model is the first diffusion-based architecture which is trained on such high resolutions entirely end-to-end. Project webpage: https://snap-research.github.io/hpdm.

We are witnessing significant breakthroughs in the tech-nology for generating 3D objects from text. Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets. Generating entire scenes, however, remains very challenging as a scene contains multiple 3D objects, diverse and scattered. In this work, we introduce SceneWiz3D - a novel approach to synthesize high-fidelity 3D scenes from text. We marry the locality of objects with globality of scenes by introducing a hybrid 3D representation - explicit for objects and implicit for scenes. Remarkably, an object, being represented explicitly, can be either generated from text using conventional text-to-3D approaches, or provided by users. To configure the layout of the scene and automatically place objects, we apply the Particle Swarm Optimization technique during the optimization process. Furthermore, it is difficult for certain parts of the scene (e.g., corners, occlusion) to receive multi-view supervision, leading to inferior geometry. We incor-porate an RGBD panorama diffusion model to mitigate it, resulting in high-quality geometry. Extensive evaluation supports that our approach achieves superior quality over previous approaches, enabling the generation of detailed and view-consistent 3D scenes. Our project website is at https://zqh0253.github.io/SceneWiz3D/.

Yuwei Fang, Willi Menapace, Aliaksandr Siarohin, Tsai-Shien Chen, Kuan-Chieh Wang, Ivan Skorokhodov, Graham Neubig, Sergey Tulyakov. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Despite significant advances in large-scale text-to-image models, achieving hyper-realistic human image generation remains a desirable yet unsolved task. Existing models like Stable Diffusion and DALL·E 2 tend to generate human images with incoherent parts or unnatural poses. To tackle these challenges, our key insight is that human image is inherently structural over multiple granularities, from the coarse-level body skeleton to fine-grained spatial geometry. Therefore, capturing such correlations between the explicit appearance and latent structure in one model is essential to generate coherent and natural human images. To this end, we propose a unified framework, HyperHuman, that generates in-the-wild human images of high realism and diverse layouts. Specifically, 1) we first build a large-scale human-centric dataset, named HumanVerse, which consists of 340M images with comprehensive annotations like human pose, depth, and surface normal. 2) Next, we propose a Latent Structural Diffusion Model that simultaneously denoises the depth and surface normal along with the synthesized RGB image. Our model enforces the joint learning of image appearance, spatial relationship, and geometry in a unified network, where each branch in the model complements to each other with both structural awareness and textural richness. 3) Finally, to further boost the visual quality, we propose a Structure-Guided Refiner to compose the predicted conditions for more detailed generation of higher resolution. Extensive experiments demonstrate that our framework yields the state-of-the-art performance, generating hyper-realistic human images under diverse scenarios.

We present ``Magic123'', a two-stage coarse-to-fine approach for high-quality, textured 3D mesh generation from a single image in the wild using *both 2D and 3D priors*. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference-view supervision and novel-view guidance by a joint 2D and 3D diffusion prior. We introduce a trade-off parameter between the 2D and 3D priors to control the details and 3D consistencies of the generation. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on diverse synthetic and real-world images.

Neural network architecture design requires making many crucial decisions. The common desiderata is that similar decisions, with little modifications, can be reused in a variety of tasks and applications. To satisfy that, architectures must provide promising latency and performance trade-offs, support a variety of tasks, scale efficiently with respect to the amounts of data and compute, leverage available data from other tasks, and efficiently support various hardware. To this end, we introduce AsCAN---a hybrid architecture, combining both convolutional and transformer blocks. We revisit the key design principles of hybrid architectures and propose a simple and effective \emph{asymmetric} architecture, where the distribution of convolutional and transformer blocks is \emph{asymmetric}, containing more convolutional blocks in the earlier stages, followed by more transformer blocks in later stages. AsCAN supports a variety of tasks: recognition, segmentation, class-conditional image generation, and features a superior trade-off between performance and latency. We then scale the same architecture to solve a large-scale text-to-image task and show state-of-the-art performance compared to the most recent public and commercial models. Notably, without performing any optimization of inference time our model shows faster execution, even when compared to works that do such optimization, highlighting the advantages and the value of our approach.

Existing dynamic scene generation methods mostly rely on distilling knowledge from pre-trained 3D generative models, which are typically fine-tuned on synthetic object datasets. As a result, the generated scenes are often object-centric and lack photorealism. To address these limitations, we introduce a novel pipeline designed for photorealistic text-to-4D scene generation, discarding the dependency on multi-view generative models and instead fully utilizing video generative models trained on diverse real-world datasets. Our method begins by generating a reference video using the video generation model. We then learn the canonical 3D representation of the video using a freeze-time video, delicately generated from the reference video. To handle inconsistencies in the freeze-time video, we jointly learn a per-frame deformation to model these imperfections. We then learn the temporal deformation based on the canonical representation to capture dynamic interactions in the reference video. The pipeline facilitates the generation of dynamic scenes with enhanced photorealism and structural integrity, viewable from multiple perspectives, thereby setting a new standard in 4D scene generation.

Diffusion-based video generation models have demonstrated remarkable success in obtaining high-fidelity videos through the iterative denoising process. However, these models require multiple denoising steps during sampling, resulting in high computational costs. In this work, we propose a novel approach to obtain single-step video generation models by leveraging adversarial training to fine-tune pre-trained video diffusion models. We show that, through the adversarial training, the multi-steps video diffusion model, i.e., Stable Video Diffusion (SVD), can be trained to perform single forward pass to synthesize high-quality videos, capturing both temporal and spatial dependencies in the video data. Extensive experiments demonstrate that our method achieves competitive generation quality of synthesized videos with significantly reduced computational overhead for the denoising process (i.e., around $23\times$ speedup compared with SVD and $6\times$ speedup compared with existing works, with even better generation quality), paving the way for real-time video synthesis and editing.

Neural video game simulators emerged as powerful tools to generate and edit videos. Their idea is to represent games as the evolution of an environment’s state driven by the actions of its agents. While such a paradigm enables users toplaya game action-by-action, its rigidity precludes more semantic forms of control. To overcome this limitation, we augment game models withpromptsspecified as a set ofnatural languageactions anddesired states. The result—a Promptable Game Model (PGM)—makes it possible for a user toplaythe game by prompting it with high- and low-level action sequences. Most captivatingly, our PGM unlocks thedirector’s mode, where the game is played by specifying goals for the agents in the form of a prompt. This requires learning “game AI,” encapsulated by our animation model, to navigate the scene using high-level constraints, play against an adversary, and devise a strategy to win a point. To render the resulting state, we use a compositional NeRF representation encapsulated in our synthesis model. To foster future research, we present newly collected, annotated and calibrated Tennis and Minecraft datasets. Our method significantly outperforms existing neural video game simulators in terms of rendering quality and unlocks applications beyond the capabilities of the current state-of-the-art. Our framework, data, and models are available at snap-research.github.io/promptable-game-models.

Modern 3D-GANs synthesize geometry and texture by training on large-scale datasets with a consistent structure. Training such models on stylized, artistic data, with often unknown, highly variable geometry, and camera information has not yet been shown possible. Can we train a 3D GAN on such artistic data, while maintaining multi-view consistency and texture quality? To this end, we propose an adaptation framework, where the source domain is a pre-trained 3D-GAN, while the target domain is a 2D-GAN trained on artistic datasets. We, then, distill the knowledge from a 2D generator to the source 3D generator. To do that, we first propose an optimization-based method to align the distributions of camera parameters across domains. Second, we propose regularizations necessary to learn high-quality texture, while avoiding degenerate geometric solutions, such as flat shapes. Third, we show a deformation-based technique for modeling exaggerated geometry of artistic domains, enabling-as a byproduct- personalized geometric editing. Finally, we propose a novel inversion method for 3D-GANs linking the latent spaces of the source and the target domains. Our contributions-for the first time-allow for the generation, editing, and animation of personalized artistic 3D avatars on artistic datasets. Project Page: https:/rameenabdal.github.io/3DAvatarGAN

Building animatable and editable models of clothed humans from raw 3D scans and poses is a challenging problem. Existing reposing methods suffer from the limited expressiveness of Linear Blend Skinning (LBS), require costly mesh extraction to generate each new pose, and typically do not preserve surface correspondences across different poses. In this work, we introduce Invertible Neural Skinning (INS) to address these shortcomings. To maintain correspondences, we propose a Pose-conditioned Invertible Network (PIN) architecture, which extends the LBS process by learning additional pose-varying deformations. Next, we combine PIN with a differentiable LBS module to build an expressive and end-to-end Invertible Neural Skinning (INS) pipeline. We demonstrate the strong performance of our method by outperforming the state-of-the-art reposing techniques on clothed humans and preserving surface correspondences, while being an order of magnitude faster. We also perform an ablation study, which shows the usefulness of our pose-conditioning formulation, and our qualitative results display that INS can rectify artefacts introduced by LBS well.

We propose a novel approach for unsupervised 3D animation of non-rigid deformable objects. Our method learns the 3D structure and dynamics of objects solely from single-view RGB videos, and can decompose them into semantically meaningful parts that can be tracked and animated. Using a 3D autodecoder framework, paired with a keypoint estimator via a differentiable PnP algorithm, our model learns the underlying object geometry and parts decomposition in an entirely unsupervised manner. This allows it to perform 3D segmentation, 3D keypoint estimation, novel view synthesis, and animation. We primarily evaluate the framework on two video datasets: VoxCeleb 2562and TEDXPeople 2562. In addition, on the Cats 2562image dataset, we show it even learns compelling 3D geometry from still images. Finally, we show our model can obtain animatable 3D objects from a single or few images11Code and visual results available on our project website: https://snap-research.github.io/unsupervised-volumetric-animation..

Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects. This work presents DisCoScene: a 3D-aware generative model for high-quality and controllable scene synthesis. The key ingredient of our method is a very abstract object-level representation (i.e., 3D bounding boxes without semantic annotation) as the scene layout prior, which is simple to obtain, general to describe various scene contents, and yet informative to disentangle objects and background. Moreover, it serves as an intuitive user control for scene editing. Based on such a prior, the proposed model spatially disentangles the whole scene into object-centric generative radiance fields by learning on only 2D images with the global-local discrimination. Our model obtains the generation fidelity and editing flexibility of individual objects while being able to efficiently compose objects and the background into a complete scene. We demonstrate state-of-the-art performance on many scene datasets, including the challenging Waymo outdoor dataset. Project page can be found here.

Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which constructs and renders an unconstrainedly large and 3D-grounded environment from random noises. InfiniCity decomposes the seemingly impractical task into three feasible modules, taking advantage of both 2D and 3D data. First, an infinite-pixel image synthesis module generates arbitrary-scale 2D maps from the bird’s-eye view. Next, an octree-based voxel completion module lifts the generated 2D map to 3D octrees. Finally, a voxel-based neural rendering module texturizes the voxels and renders 2D images. InfiniCity can thus synthesize arbitrary-scale and traversable 3D city environments. We quantitatively and qualitatively demonstrate the efficacy of the proposed framework.

Diffusion-based methods have shown impressive visual results in the text-to-image domain. They first learn a latent space using an autoencoder, then run a denoising process on the bottleneck to generate new samples. However, learning an autoencoder requires substantial data in the target domain. Such data is scarce for 3D generation, prohibiting the learning of large-scale diffusion models for 3D synthesis. We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space, which can then be decoded into a volumetric representation for rendering view-consistent appearance and geometry. We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations to learn a 3D diffusion from 2D images or monocular videos of rigid or articulated objects. Our approach is flexible enough to use either existing camera supervision or no camera information at all -- instead efficiently learning it during training. Our evaluations demonstrate that our generation results outperform state-of-the-art alternatives on various benchmark datasets and metrics, including multi-view image datasets of synthetic objects, real in-the-wild videos of moving people, and a large-scale, real video dataset of static objects.

In this paper, we present a method for generating consistent novel views from a single source image. Our approach focuses on maximizing the reuse of visible pixels from the source image. To achieve this, we use a monocular depth estimator that transfers visible pixels from the source view to the target view. Starting from a pre-trained 2D inpainting diffusion model, we train our method on the large-scale Objaverse dataset to learn 3D object priors. While training we use a novel masking mechanism based on epipolar lines to further improve the quality of our approach. This allows our framework to perform zero-shot novel view synthesis on a variety of objects. We evaluate the zero-shot abilities of our framework on three challenging datasets: Google Scanned Objects, Ray Traced Multiview, and Common Objects in 3D.

We introduce Text2Cinemagraph, a fully automated method for creating cinemagraphs from text descriptions --- an especially challenging task when prompts feature imaginary elements and artistic styles, given the complexity of interpreting the semantics and motions of these images. We focus on cinemagraphs of fluid elements, such as flowing rivers, and drifting clouds, which exhibit continuous motion and repetitive textures. Existing single-image animation methods fall short on artistic inputs, and recent text-based video methods frequently introduce temporal inconsistencies, struggling to keep certain regions static. To address these challenges, we propose an idea of synthesizing image twins from a single text prompt --- a pair of an artistic image and its pixel-aligned corresponding natural-looking twin. While the artistic image depicts the style and appearance detailed in our text prompt, the realistic counterpart greatly simplifies layout and motion analysis. Leveraging existing natural image and video datasets, we can accurately segment the realistic image and predict plausible motion given the semantic information. The predicted motion can then be transferred to the artistic image to create the final cinemagraph. Our method outperforms existing approaches in creating cinemagraphs for natural landscapes as well as artistic and other-worldly scenes, as validated by automated metrics and user studies. Finally, we demonstrate two extensions: animating existing paintings and controlling motion directions using text.

We present Playable Environments-a new representation for interactive video generation and manipulation in space and time. With a single image at inference time, our novel framework allows the user to move objects in 3D while generating a video by providing a sequence of desired actions. The actions are learnt in an unsupervised manner. The camera can be controlled to get the desired viewpoint. Our method builds an environment state for each frame, which can be manipulated by our proposed action mod-ule and decoded back to the image space with volumetric rendering. To support diverse appearances of objects, we extend neural radiance fields with style-based modulation. Our method trains on a collection of various monocular videos requiring only the estimated camera parameters and 2D object locations. To set a challenging benchmark, we in-troduce two large scale video datasets with significant cam-era movements. As evidenced by our experiments, playable environments enable several creative applications not at-tainable by prior video synthesis works, including playable 3D video generation, stylization and manipulation11willi-menapace.github.io/playable-environments-website.

This paper introduces the unsupervised learning problem of playable video generation (PVG). In PVG, we aim at allowing a user to control the generated video by selecting a discrete action at every time step as when playing a video game. The difficulty of the task lies both in learning semantically consistent actions and in generating realistic videos conditioned on the user input. We propose a novel framework for PVG that is trained in a self-supervised manner on a large dataset of unlabelled videos. We employ an encoder-decoder architecture where the predicted action labels act as bottleneck. The network is constrained to learn a rich action space using, as main driving loss, a reconstruction loss on the generated video. We demonstrate the effectiveness of the proposed approach on several datasets with wide environment variety. Further details, code and examples are available on our project page willi-menapace.github.io/playable-video-generation-website.

We propose novel motion representations for animating articulated objects consisting of distinct parts. In a completely unsupervised manner, our method identifies object parts, tracks them in a driving video, and infers their motions by considering their principal axes. In contrast to the previous keypoint-based works, our method extracts meaningful and consistent regions, describing locations, shape, and pose. The regions correspond to semantically relevant and distinct object parts, that are more easily detected in frames of the driving video. To force decoupling of foreground from background, we model non-object related global motion with an additional affine transformation. To facilitate animation and prevent the leakage of the shape of the driving object, we disentangle shape and pose of objects in the region space. Our model1can animate a variety of objects, surpassing previous methods by a large margin on existing benchmarks. We present a challenging new benchmark with high-resolution videos and show that the improvement is particularly pronounced when articulated objects are considered, reaching 96.6% user preference vs. the state of the art.

Most of the current self-supervised representation learning (SSL) methods are based on the contrastive loss and the instance-discrimination task, where augmented versions of the same image instance ("positives") are contrasted with instances extracted from other images ("negatives"). For the learning to be effective, many negatives should be compared with a positive pair, which is computationally demanding. In this paper, we propose a different direction and a new loss function for SSL, which is based on the whitening of the latent-space features. The whitening operation has a "scattering" effect on the batch samples, avoiding degenerate solutions where all the sample representations collapse to a single point. Our solution does not require asymmetric networks and it is conceptually simple. Moreover, since negatives are not needed, we can extract multiple positive pairs from the same image instance. The source code of the method and of all the experiments is available at: https://github.com/htdt/self-supervised.

Abstract Most domain adaptation methods consider the problem of transferring knowledge to the target domain from a single-source dataset. However, in practical applications, we typically have access to multiple sources. In this paper we propose the first approach for multi-source domain adaptation (MSDA) based on generative adversarial networks. Our method is inspired by the observation that the appearance of a given image depends on three factors: thedomain, thestyle(characterized in terms of low-level features variations) and thecontent. For this reason, we propose to project the source image features onto a space where only the dependence from the content is kept, and then re-project this invariant representation onto the pixel space using the target domain and style. In this way, new labeled images can be generated which are used to train a final target classifier. We test our approach using common MSDA benchmarks, showing that it outperforms state-of-the-art methods.

In this paper, we address the problem of generating person images conditioned on both pose and appearance information. Specifically, given an image xaof a person and a target pose P(xb), extracted from an image xb, we synthesize a new image of that person in pose P(xb), while preserving the visual details in xa. In orderto deal with pixel-to-pixel misalignments caused bythe pose differences between P(xa) and P(xb), we introduce deformable skip connections in the generator of our Generative Adversarial Network. Moreover, a nearest-neighbour loss is proposed instead of the common L1and L2losses in order to match the details of the generated image with the target image. Quantitative and qualitative results, using common datasets and protocols recently proposed for this task, show that our approach is competitive with respect to the state of the art. Moreover, we conduct an extensive evaluation using off-the-shell person re-identification (Re-ID) systems trained with person-generation based augmented data, which is one of the main important applications for this task. Our experiments show that our Deformable GANs can significantly boost the Re-ID accuracy and are even better than data-augmentation methods specifically trained using Re-ID losses.

Recent co-part segmentation methods mostly operate in a supervised learning setting, which requires a large amount of annotated data for training. To overcome this limitation, we propose a self-supervised deep learning method for co-part segmentation. Differently from previous works, our approach develops the idea that motion information inferred from videos can be leveraged to discover meaningful object parts. To this end, our method relies on pairs of frames sampled from the same video. The network learns to predict part segments together with a representation of the motion between two frames, which permits reconstruction of the target image. Through extensive experimental evaluation on publicly available video sequences we demonstrate that our approach can produce improved segmentation maps with respect to previous self-supervised co-part segmentation approaches.

We present a generalization of the person-image generation task, in which a human image is generated conditioned on a target pose and a set X of source appearance images. In this way, we can exploit multiple, possibly complementary images of the same person which are usually available at training and at testing time. The solution we propose is mainly based on a local attention mechanism which selects relevant information from different source image regions, avoiding the necessity to build specific generators for each specific cardinality of X. The empirical evaluation of our method shows the practical interest of addressing the person-image generation problem in a multi-source setting.

A classifier trained on a dataset seldom works on other datasets obtained under different conditions due to domain shift. This problem is commonly addressed by domain adaptation methods. In this work we introduce a novel deep learning framework which unifies different paradigms in unsupervised domain adaptation. Specifically, we propose domain alignment layers which implement feature whitening for the purpose of matching source and target feature distributions. Additionally, we leverage the unlabeled target data by proposing the Min-Entropy Consensus loss, which regularizes training while avoiding the adoption of many user-defined hyper-parameters. We report results on publicly available datasets, considering both digit classification and object recognition tasks. We show that, in most of our experiments, our approach improves upon previous methods, setting new state-of-the-art performances.

This paper introduces a novel deep learning framework for image animation. Given an input image with a target object and a driving video sequence depicting a moving object, our framework generates a video in which the target object is animated according to the driving sequence. This is achieved through a deep architecture that decouples appearance and motion information. Our framework consists of three main modules: (i) a Keypoint Detector unsupervisely trained to extract object keypoints, (ii) a Dense Motion prediction network for generating dense heatmaps from sparse keypoints, in order to better encode motion information and (iii) a Motion Transfer Network, which uses the motion heatmaps and appearance information extracted from the input image to synthesize the output frames. We demonstrate the effectiveness of our method on several benchmark datasets, spanning a wide variety of object appearances, and show that our approach outperforms state-of-the-art image animation and video generation methods.

Image animation consists of generating a video sequence so that an object in a source image is animated according to the motion of a driving video. Our framework addresses this problem without using any annotation or prior information about the specific object to animate. Once trained on a set of videos depicting objects of the same category (e.g. faces, human bodies), our method can be applied to any object of this class. To achieve this, we decouple appearance and motion information using a self-supervised formulation. To support complex motions, we use a representation consisting of a set of learned keypoints along with their local affine transformations. A generator network models occlusions arising during target motions and combines the appearance extracted from the source image and the motion derived from the driving video. Our framework scores best on diverse benchmarks and on a variety of object categories.

Recent works in computer vision and multimedia have shown that image memorability can be automatically inferred exploiting powerful deep-learning models. This article advances the state of the art in this area by addressing a novel and more challenging issue: “ Given an arbitrary input image, can we make it more memorable? ” To tackle this problem, we introduce an approach based on an editing-by-applying-filters paradigm: given an input image, we propose to automatically retrieve a set of “style seeds,” i.e., a set of style images that, applied to the input image through a neural style transfer algorithm, provide the highest increase in memorability. We show the effectiveness of the proposed approach with experiments on the publicly available LaMem dataset, performing both a quantitative evaluation and a user study. To demonstrate the flexibility of the proposed framework, we also analyze the impact of different implementation choices, such as using different state-of-the-art neural style transfer methods. Finally, we show several qualitative results to provide additional insights on the link between image style and memorability.

In this paper we address the problem of generating person images conditioned on a given pose. Specifically, given an image of a person and a target pose, we synthesize a new image of that person in the novel pose. In order to deal with pixel-to-pixel misalignments caused by the pose differences, we introduce deformable skip connections in the generator of our Generative Adversarial Network. Moreover, a nearest-neighbour loss is proposed instead of the common L1and L2losses in order to match the details of the generated image with the target image. We test our approach using photos of persons in different poses and we compare our method with previous work in this area showing state-of-the-art results in two benchmarks. Our method can be applied to the wider field of deformable object generation, provided that the pose of the articulated object can be extracted using a keypoint detector.

Recent works have shown that it is possible to automatically predict intrinsic image properties like memorability. In this paper, we take a step forward addressing the question: "Can we make an image more memorable?". Methods for automatically increasing image memorability would have an impact in many application fields like education, gaming or advertising. Our work is inspired by the popular editing-by-applying-filters paradigm adopted in photo editing applications, like Instagram and Prisma. In this context, the problem of increasing image memorability maps to that of retrieving ``memorabilizing'' filters or style ``seeds''. Still, users generally have to go through most of the available filters before finding the desired solution, thus turning the editing process into a resource and time consuming task. In this work, we show that it is possible to automatically retrieve the best style seeds for a given image, thus remarkably reducing the number of human attempts needed to find a good match. Our approach leverages from recent advances in the field of image synthesis and adopts a deep architecture for generating a memorable picture from a given input image and a style seed. Importantly, to automatically select the best style a novel learning-based solution, also relying on deep models, is proposed. Our experimental evaluation, conducted on publicly available benchmarks, demonstrates the effectiveness of the proposed approach for generating memorable images through automatic style seed selection.