Albert Pumarola

Yu-Jhe Li, Tao Xu, Ji Hou et al. · cmu

We tackle the task of text-to-3D creation with pre-trained latent-based NeRFs (NeRFs that generate 3D objects given input latent code). Recent works such as DreamFusion and Magic3D have shown great success in generating 3D content using NeRFs and text prompts, but the current approach of optimizing a NeRF for every text prompt is 1) extremely time-consuming and 2) often leads to low-resolution outputs. To address these challenges, we propose a novel method named 3D-CLFusion which leverages the pre-trained latent-based NeRFs and performs fast 3D content creation in less than a minute. In particular, we introduce a latent diffusion prior network for learning the w latent from the input CLIP text/image embeddings. This pipeline allows us to produce the w latent without further optimization during inference and the pre-trained NeRF is able to perform multi-view high-resolution 3D synthesis based on the latent. We note that the novelty of our model lies in that we introduce contrastive learning during training the diffusion prior which enables the generation of the valid view-invariant latent code. We demonstrate through experiments the effectiveness of our proposed view-invariant diffusion process for fast text-to-3D creation, e.g., 100 times faster than DreamFusion. We note that our model is able to serve as the role of a plug-and-play tool for text-to-3D with pre-trained NeRFs.

Yu-Jhe Li, Tao Xu, Bichen Wu et al. · cmu

We tackle the task of NeRF inversion for style-based neural radiance fields, (e.g., StyleNeRF). In the task, we aim to learn an inversion function to project an input image to the latent space of a NeRF generator and then synthesize novel views of the original image based on the latent code. Compared with GAN inversion for 2D generative models, NeRF inversion not only needs to 1) preserve the identity of the input image, but also 2) ensure 3D consistency in generated novel views. This requires the latent code obtained from the single-view image to be invariant across multiple views. To address this new challenge, we propose a two-stage encoder for style-based NeRF inversion. In the first stage, we introduce a base encoder that converts the input image to a latent code. To ensure the latent code is view-invariant and is able to synthesize 3D consistent novel view images, we utilize identity contrastive learning to train the base encoder. Second, to better preserve the identity of the input image, we introduce a refining encoder to refine the latent code and add finer details to the output image. Importantly note that the novelty of this model lies in the design of its first-stage encoder which produces the closest latent code lying on the latent manifold and thus the refinement in the second stage would be close to the NeRF manifold. Through extensive experiments, we demonstrate that our proposed two-stage encoder qualitatively and quantitatively exhibits superiority over the existing encoders for inversion in both image reconstruction and novel-view rendering.

Sara Rojas, Jesus Zarzar, Juan Camilo Perez et al.

This paper proposes a novel approach for rendering a pre-trained Neural Radiance Field (NeRF) in real-time on resource-constrained devices. We introduce Re-ReND, a method enabling Real-time Rendering of NeRFs across Devices. Re-ReND is designed to achieve real-time performance by converting the NeRF into a representation that can be efficiently processed by standard graphics pipelines. The proposed method distills the NeRF by extracting the learned density into a mesh, while the learned color information is factorized into a set of matrices that represent the scene's light field. Factorization implies the field is queried via inexpensive MLP-free matrix multiplications, while using a light field allows rendering a pixel by querying the field a single time-as opposed to hundreds of queries when employing a radiance field. Since the proposed representation can be implemented using a fragment shader, it can be directly integrated with standard rasterization frameworks. Our flexible implementation can render a NeRF in real-time with low memory requirements and on a wide range of resource-constrained devices, including mobiles and AR/VR headsets. Notably, we find that Re-ReND can achieve over a 2.6-fold increase in rendering speed versus the state-of-the-art without perceptible losses in quality.

Neta Shaul, Juan Perez, Ricky T. Q. Chen et al.

Diffusion or flow-based models are powerful generative paradigms that are notoriously hard to sample as samples are defined as solutions to high-dimensional Ordinary or Stochastic Differential Equations (ODEs/SDEs) which require a large Number of Function Evaluations (NFE) to approximate well. Existing methods to alleviate the costly sampling process include model distillation and designing dedicated ODE solvers. However, distillation is costly to train and sometimes can deteriorate quality, while dedicated solvers still require relatively large NFE to produce high quality samples. In this paper we introduce "Bespoke solvers", a novel framework for constructing custom ODE solvers tailored to the ODE of a given pre-trained flow model. Our approach optimizes an order consistent and parameter-efficient solver (e.g., with 80 learnable parameters), is trained for roughly 1% of the GPU time required for training the pre-trained model, and significantly improves approximation and generation quality compared to dedicated solvers. For example, a Bespoke solver for a CIFAR10 model produces samples with Fréchet Inception Distance (FID) of 2.73 with 10 NFE, and gets to 1% of the Ground Truth (GT) FID (2.59) for this model with only 20 NFE. On the more challenging ImageNet-64$\times$64, Bespoke samples at 2.2 FID with 10 NFE, and gets within 2% of GT FID (1.71) with 20 NFE.

Albert Pumarola, Artsiom Sanakoyeu, Lior Yariv et al.

Surface reconstruction has been seeing a lot of progress lately by utilizing Implicit Neural Representations (INRs). Despite their success, INRs often introduce hard to control inductive bias (i.e., the solution surface can exhibit unexplainable behaviours), have costly inference, and are slow to train. The goal of this work is to show that replacing neural networks with simple grid functions, along with two novel geometric priors achieve comparable results to INRs, with instant inference, and improved training times. To that end we introduce VisCo Grids: a grid-based surface reconstruction method incorporating Viscosity and Coarea priors. Intuitively, the Viscosity prior replaces the smoothness inductive bias of INRs, while the Coarea favors a minimal area solution. Experimenting with VisCo Grids on a standard reconstruction baseline provided comparable results to the best performing INRs on this dataset.

Yuming Du, Robin Kips, Albert Pumarola et al.

With the recent surge in popularity of AR/VR applications, realistic and accurate control of 3D full-body avatars has become a highly demanded feature. A particular challenge is that only a sparse tracking signal is available from standalone HMDs (Head Mounted Devices), often limited to tracking the user's head and wrists. While this signal is resourceful for reconstructing the upper body motion, the lower body is not tracked and must be synthesized from the limited information provided by the upper body joints. In this paper, we present AGRoL, a novel conditional diffusion model specifically designed to track full bodies given sparse upper-body tracking signals. Our model is based on a simple multi-layer perceptron (MLP) architecture and a novel conditioning scheme for motion data. It can predict accurate and smooth full-body motion, particularly the challenging lower body movement. Unlike common diffusion architectures, our compact architecture can run in real-time, making it suitable for online body-tracking applications. We train and evaluate our model on AMASS motion capture dataset, and demonstrate that our approach outperforms state-of-the-art methods in generated motion accuracy and smoothness. We further justify our design choices through extensive experiments and ablation studies.

Angela Castillo, Maria Escobar, Guillaume Jeanneret et al.

Mixed reality applications require tracking the user's full-body motion to enable an immersive experience. However, typical head-mounted devices can only track head and hand movements, leading to a limited reconstruction of full-body motion due to variability in lower body configurations. We propose BoDiffusion -- a generative diffusion model for motion synthesis to tackle this under-constrained reconstruction problem. We present a time and space conditioning scheme that allows BoDiffusion to leverage sparse tracking inputs while generating smooth and realistic full-body motion sequences. To the best of our knowledge, this is the first approach that uses the reverse diffusion process to model full-body tracking as a conditional sequence generation task. We conduct experiments on the large-scale motion-capture dataset AMASS and show that our approach outperforms the state-of-the-art approaches by a significant margin in terms of full-body motion realism and joint reconstruction error.

Chaojian Li, Bichen Wu, Albert Pumarola et al.

We present a method that accelerates reconstruction of 3D scenes and objects, aiming to enable instant reconstruction on edge devices such as mobile phones and AR/VR headsets. While recent works have accelerated scene reconstruction training to minute/second-level on high-end GPUs, there is still a large gap to the goal of instant training on edge devices which is yet highly desired in many emerging applications such as immersive AR/VR. To this end, this work aims to further accelerate training by leveraging geometry priors of the target scene. Our method proposes strategies to alleviate the noise of the imperfect geometry priors to accelerate the training speed on top of the highly optimized Instant-NGP. On the NeRF Synthetic dataset, our work uses half of the training iterations to reach an average test PSNR of >30.

Nicolas Ugrinovic, Albert Pumarola, Alberto Sanfeliu et al.

Recent advances in 3D human shape reconstruction from single images have shown impressive results, leveraging on deep networks that model the so-called implicit function to learn the occupancy status of arbitrarily dense 3D points in space. However, while current algorithms based on this paradigm, like PiFuHD, are able to estimate accurate geometry of the human shape and clothes, they require high-resolution input images and are not able to capture complex body poses. Most training and evaluation is performed on 1k-resolution images of humans standing in front of the camera under neutral body poses. In this paper, we leverage publicly available data to extend existing implicit function-based models to deal with images of humans that can have arbitrary poses and self-occluded limbs. We argue that the representation power of the implicit function is not sufficient to simultaneously model details of the geometry and of the body pose. We, therefore, propose a coarse-to-fine approach in which we first learn an implicit function that maps the input image to a 3D body shape with a low level of detail, but which correctly fits the underlying human pose, despite its complexity. We then learn a displacement map, conditioned on the smoothed surface and on the input image, which encodes the high-frequency details of the clothes and body. In the experimental section, we show that this coarse-to-fine strategy represents a very good trade-off between shape detail and pose correctness, comparing favorably to the most recent state-of-the-art approaches. Our code will be made publicly available.

Boxun Xu, Yuming Du, Zichang Liu et al.

We introduce Sparse Forcing, a training-and-inference paradigm for autoregressive video diffusion models that improves long-horizon generation quality while reducing decoding latency. Sparse Forcing is motivated by an empirical observation in autoregressive diffusion rollouts: attention concentrates on a persistent subset of salient visual blocks, forming an implicit spatiotemporal memory in the KV cache, and exhibits a locally structured block-sparse pattern within sliding windows. Building on this observation, we propose a trainable native sparsity mechanism that learns to compress, preserve, and update these persistent blocks while restricting computation within each local window to a dynamically selected local neighborhood. To make the approach practical at scale for both training and inference, we further propose Persistent Block-Sparse Attention (PBSA), an efficient GPU kernel that accelerates sparse attention and memory updates for low-latency, memory-efficient decoding. Experiments show that Sparse Forcing improves the VBench score by +0.26 over Self-Forcing on 5-second text-to-video generation while delivering a 1.11-1.17x decoding speedup and 42% lower peak KV-cache footprint. The gains are more pronounced on longer-horizon rollouts, delivering improved visual quality with +0.68 and +2.74 VBench improvements, and 1.22x and 1.27x speedups on 20-second and 1-minute generations, respectively.

Cheeun Hong, German Barquero, Fadime Sener et al.

Instructional video generation is an emerging task that aims to synthesize coherent demonstrations of procedural activities from textual descriptions. Such capability has broad implications for content creation, education, and human-AI interaction, yet existing video diffusion models struggle to maintain temporal consistency and controllability across long sequences of multiple action steps. We introduce a pipeline for future-driven streaming instructional video generation, dubbed SneakPeek, a diffusion-based autoregressive framework designed to generate precise, stepwise instructional videos conditioned on an initial image and structured textual prompts. Our approach introduces three key innovations to enhance consistency and controllability: (1) predictive causal adaptation, where a causal model learns to perform next-frame prediction and anticipate future keyframes; (2) future-guided self-forcing with a dual-region KV caching scheme to address the exposure bias issue at inference time; (3) multi-prompt conditioning, which provides fine-grained and procedural control over multi-step instructions. Together, these components mitigate temporal drift, preserve motion consistency, and enable interactive video generation where future prompt updates dynamically influence ongoing streaming video generation. Experimental results demonstrate that our method produces temporally coherent and semantically faithful instructional videos that accurately follow complex, multi-step task descriptions.

Adam Polyak, Amit Zohar, Andrew Brown et al. · meta-ai

We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models. All videos from this paper are available at https://go.fb.me/MovieGenResearchVideos.

Yeongmin Kim, Sotiris Anagnostidis, Yuming Du et al.

Diffusion models with transformer architectures have demonstrated promising capabilities in generating high-fidelity images and scalability for high resolution. However, iterative sampling process required for synthesis is very resource-intensive. A line of work has focused on distilling solutions to probability flow ODEs into few-step student models. Nevertheless, existing methods have been limited by their reliance on the most recent denoised samples as input, rendering them susceptible to exposure bias. To address this limitation, we propose AutoRegressive Distillation (ARD), a novel approach that leverages the historical trajectory of the ODE to predict future steps. ARD offers two key benefits: 1) it mitigates exposure bias by utilizing a predicted historical trajectory that is less susceptible to accumulated errors, and 2) it leverages the previous history of the ODE trajectory as a more effective source of coarse-grained information. ARD modifies the teacher transformer architecture by adding token-wise time embedding to mark each input from the trajectory history and employs a block-wise causal attention mask for training. Furthermore, incorporating historical inputs only in lower transformer layers enhances performance and efficiency. We validate the effectiveness of ARD in a class-conditioned generation on ImageNet and T2I synthesis. Our model achieves a $5\times$ reduction in FID degradation compared to the baseline methods while requiring only 1.1\% extra FLOPs on ImageNet-256. Moreover, ARD reaches FID of 1.84 on ImageNet-256 in merely 4 steps and outperforms the publicly available 1024p text-to-image distilled models in prompt adherence score with a minimal drop in FID compared to the teacher. Project page: https://github.com/alsdudrla10/ARD.

Jonas Kohler, Albert Pumarola, Edgar Schönfeld et al.

Diffusion models are a powerful generative framework, but come with expensive inference. Existing acceleration methods often compromise image quality or fail under complex conditioning when operating in an extremely low-step regime. In this work, we propose a novel distillation framework tailored to enable high-fidelity, diverse sample generation using just one to three steps. Our approach comprises three key components: (i) Backward Distillation, which mitigates training-inference discrepancies by calibrating the student on its own backward trajectory; (ii) Shifted Reconstruction Loss that dynamically adapts knowledge transfer based on the current time step; and (iii) Noise Correction, an inference-time technique that enhances sample quality by addressing singularities in noise prediction. Through extensive experiments, we demonstrate that our method outperforms existing competitors in quantitative metrics and human evaluations. Remarkably, it achieves performance comparable to the teacher model using only three denoising steps, enabling efficient high-quality generation.

Gregor Bachmann, Sotiris Anagnostidis, Albert Pumarola et al.

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive generation, leveraging a fast draft model to propose candidate tokens, which are then verified in parallel based on their likelihood under the target model. While this approach guarantees to reproduce the target output, it incurs a substantial penalty: many high-quality draft tokens are rejected, even when they represent objectively valid continuations. Indeed, we show that even powerful draft models such as GPT-4o, as well as human text cannot achieve high acceptance rates under the standard verification scheme. This severely limits the speedup potential of current speculative decoding methods, as an early rejection becomes overwhelmingly likely when solely relying on alignment of draft and target. We thus ask the following question: Can we adapt verification to recognize correct, but non-aligned replies? To this end, we draw inspiration from the LLM-as-a-judge framework, which demonstrated that LLMs are able to rate answers in a versatile way. We carefully design a dataset to elicit the same capability in the target model by training a compact module on top of the embeddings to produce ``judgements" of the current continuation. We showcase our strategy on the Llama-3.1 family, where our 8b/405B-Judge achieves a speedup of 9x over Llama-405B, while maintaining its quality on a large range of benchmarks. These benefits remain present even in optimized inference frameworks, where our method reaches up to 141 tokens/s for 8B/70B-Judge and 129 tokens/s for 8B/405B on 2 and 8 H100s respectively.

Angela Castillo, Jonas Kohler, Juan C. Pérez et al.

This paper presents a comprehensive study on the role of Classifier-Free Guidance (CFG) in text-conditioned diffusion models from the perspective of inference efficiency. In particular, we relax the default choice of applying CFG in all diffusion steps and instead search for efficient guidance policies. We formulate the discovery of such policies in the differentiable Neural Architecture Search framework. Our findings suggest that the denoising steps proposed by CFG become increasingly aligned with simple conditional steps, which renders the extra neural network evaluation of CFG redundant, especially in the second half of the denoising process. Building upon this insight, we propose "Adaptive Guidance" (AG), an efficient variant of CFG, that adaptively omits network evaluations when the denoising process displays convergence. Our experiments demonstrate that AG preserves CFG's image quality while reducing computation by 25%. Thus, AG constitutes a plug-and-play alternative to Guidance Distillation, achieving 50% of the speed-ups of the latter while being training-free and retaining the capacity to handle negative prompts. Finally, we uncover further redundancies of CFG in the first half of the diffusion process, showing that entire neural function evaluations can be replaced by simple affine transformations of past score estimates. This method, termed LinearAG, offers even cheaper inference at the cost of deviating from the baseline model. Our findings provide insights into the efficiency of the conditional denoising process that contribute to more practical and swift deployment of text-conditioned diffusion models.

Neta Shaul, Uriel Singer, Ricky T. Q. Chen et al.

This paper introduces Bespoke Non-Stationary (BNS) Solvers, a solver distillation approach to improve sample efficiency of Diffusion and Flow models. BNS solvers are based on a family of non-stationary solvers that provably subsumes existing numerical ODE solvers and consequently demonstrate considerable improvement in sample approximation (PSNR) over these baselines. Compared to model distillation, BNS solvers benefit from a tiny parameter space ($<$200 parameters), fast optimization (two orders of magnitude faster), maintain diversity of samples, and in contrast to previous solver distillation approaches nearly close the gap from standard distillation methods such as Progressive Distillation in the low-medium NFE regime. For example, BNS solver achieves 45 PSNR / 1.76 FID using 16 NFE in class-conditional ImageNet-64. We experimented with BNS solvers for conditional image generation, text-to-image generation, and text-2-audio generation showing significant improvement in sample approximation (PSNR) in all.

Sotiris Anagnostidis, Gregor Bachmann, Yeongmin Kim et al.

Despite their remarkable performance, modern Diffusion Transformers are hindered by substantial resource requirements during inference, stemming from the fixed and large amount of compute needed for each denoising step. In this work, we revisit the conventional static paradigm that allocates a fixed compute budget per denoising iteration and propose a dynamic strategy instead. Our simple and sample-efficient framework enables pre-trained DiT models to be converted into \emph{flexible} ones -- dubbed FlexiDiT -- allowing them to process inputs at varying compute budgets. We demonstrate how a single \emph{flexible} model can generate images without any drop in quality, while reducing the required FLOPs by more than $40$\% compared to their static counterparts, for both class-conditioned and text-conditioned image generation. Our method is general and agnostic to input and conditioning modalities. We show how our approach can be readily extended for video generation, where FlexiDiT models generate samples with up to $75$\% less compute without compromising performance.

Jonas Kohler, Nicolas Griffiths Sanchez, Luca Cavalli et al.

In this study, we propose two novel input processing paradigms for novel view synthesis (NVS) methods based on layered scene representations that significantly improve their runtime without compromising quality. Our approach identifies and mitigates the two most time-consuming aspects of traditional pipelines: building and processing the so-called plane sweep volume (PSV), which is a high-dimensional tensor of planar re-projections of the input camera views. In particular, we propose processing this tensor in parallel groups for improved compute efficiency as well as super-sampling adjacent input planes to generate denser, and hence more accurate scene representation. The proposed enhancements offer significant flexibility, allowing for a balance between performance and speed, thus making substantial steps toward real-time applications. Furthermore, they are very general in the sense that any PSV-based method can make use of them, including methods that employ multiplane images, multisphere images, and layered depth images. In a comprehensive set of experiments, we demonstrate that our proposed paradigms enable the design of an NVS method that achieves state-of-the-art on public benchmarks while being up to $50x$ faster than existing state-of-the-art methods. It also beats the current forerunner in terms of speed by over $3x$, while achieving significantly better rendering quality.

David Yan, Winnie Zhang, Luxin Zhang et al.

We introduce animated stickers, a video diffusion model which generates an animation conditioned on a text prompt and static sticker image. Our model is built on top of the state-of-the-art Emu text-to-image model, with the addition of temporal layers to model motion. Due to the domain gap, i.e. differences in visual and motion style, a model which performed well on generating natural videos can no longer generate vivid videos when applied to stickers. To bridge this gap, we employ a two-stage finetuning pipeline: first with weakly in-domain data, followed by human-in-the-loop (HITL) strategy which we term ensemble-of-teachers. It distills the best qualities of multiple teachers into a smaller student model. We show that this strategy allows us to specifically target improvements to motion quality while maintaining the style from the static image. With inference optimizations, our model is able to generate an eight-frame video with high-quality, interesting, and relevant motion in under one second.

Ameya Dhamanaskar, Mariella Dimiccoli, Enric Corona et al.

In this paper, we propose a novel approach to enhance the 3D body pose estimation of a person computed from videos captured from a single wearable camera. The key idea is to leverage high-level features linking first- and third-views in a joint embedding space. To learn such embedding space we introduce First2Third-Pose, a new paired synchronized dataset of nearly 2,000 videos depicting human activities captured from both first- and third-view perspectives. We explicitly consider spatial- and motion-domain features, combined using a semi-Siamese architecture trained in a self-supervised fashion. Experimental results demonstrate that the joint multi-view embedded space learned with our dataset is useful to extract discriminatory features from arbitrary single-view egocentric videos, without needing domain adaptation nor knowledge of camera parameters. We achieve significant improvement of egocentric 3D body pose estimation performance on two unconstrained datasets, over three supervised state-of-the-art approaches. Our dataset and code will be available for research purposes.

Jordi Sanchez-Riera, Albert Pumarola, Francesc Moreno-Noguer

We introduce PhysXNet, a learning-based approach to predict the dynamics of deformable clothes given 3D skeleton motion sequences of humans wearing these clothes. The proposed model is adaptable to a large variety of garments and changing topologies, without need of being retrained. Such simulations are typically carried out by physics engines that require manual human expertise and are subjectto computationally intensive computations. PhysXNet, by contrast, is a fully differentiable deep network that at inference is able to estimate the geometry of dense cloth meshes in a matter of milliseconds, and thus, can be readily deployed as a layer of a larger deep learning architecture. This efficiency is achieved thanks to the specific parameterization of the clothes we consider, based on 3D UV maps encoding spatial garment displacements. The problem is then formulated as a mapping between the human kinematics space (represented also by 3D UV maps of the undressed body mesh) into the clothes displacement UV maps, which we learn using a conditional GAN with a discriminator that enforces feasible deformations. We train simultaneously our model for three garment templates, tops, bottoms and dresses for which we simulate deformations under 50 different human actions. Nevertheless, the UV map representation we consider allows encapsulating many different cloth topologies, and at test we can simulate garments even if we did not specifically train for them. A thorough evaluation demonstrates that PhysXNet delivers cloth deformations very close to those computed with the physical engine, opening the door to be effectively integrated within deeplearning pipelines.

Eduard Ramon, Gil Triginer, Janna Escur et al.

Recent learning approaches that implicitly represent surface geometry using coordinate-based neural representations have shown impressive results in the problem of multi-view 3D reconstruction. The effectiveness of these techniques is, however, subject to the availability of a large number (several tens) of input views of the scene, and computationally demanding optimizations. In this paper, we tackle these limitations for the specific problem of few-shot full 3D head reconstruction, by endowing coordinate-based representations with a probabilistic shape prior that enables faster convergence and better generalization when using few input images (down to three). First, we learn a shape model of 3D heads from thousands of incomplete raw scans using implicit representations. At test time, we jointly overfit two coordinate-based neural networks to the scene, one modeling the geometry and another estimating the surface radiance, using implicit differentiable rendering. We devise a two-stage optimization strategy in which the learned prior is used to initialize and constrain the geometry during an initial optimization phase. Then, the prior is unfrozen and fine-tuned to the scene. By doing this, we achieve high-fidelity head reconstructions, including hair and shoulders, and with a high level of detail that consistently outperforms both state-of-the-art 3D Morphable Models methods in the few-shot scenario, and non-parametric methods when large sets of views are available.

Enric Corona, Albert Pumarola, Guillem Alenyà et al.

In this paper we introduce SMPLicit, a novel generative model to jointly represent body pose, shape and clothing geometry. In contrast to existing learning-based approaches that require training specific models for each type of garment, SMPLicit can represent in a unified manner different garment topologies (e.g. from sleeveless tops to hoodies and to open jackets), while controlling other properties like the garment size or tightness/looseness. We show our model to be applicable to a large variety of garments including T-shirts, hoodies, jackets, shorts, pants, skirts, shoes and even hair. The representation flexibility of SMPLicit builds upon an implicit model conditioned with the SMPL human body parameters and a learnable latent space which is semantically interpretable and aligned with the clothing attributes. The proposed model is fully differentiable, allowing for its use into larger end-to-end trainable systems. In the experimental section, we demonstrate SMPLicit can be readily used for fitting 3D scans and for 3D reconstruction in images of dressed people. In both cases we are able to go beyond state of the art, by retrieving complex garment geometries, handling situations with multiple clothing layers and providing a tool for easy outfit editing. To stimulate further research in this direction, we will make our code and model publicly available at http://www.iri.upc.edu/people/ecorona/smplicit/.

ShahRukh Athar, Albert Pumarola, Francesc Moreno-Noguer et al.

Facial Expressions induce a variety of high-level details on the 3D face geometry. For example, a smile causes the wrinkling of cheeks or the formation of dimples, while being angry often causes wrinkling of the forehead. Morphable Models (3DMMs) of the human face fail to capture such fine details in their PCA-based representations and consequently cannot generate such details when used to edit expressions. In this work, we introduce FaceDet3D, a first-of-its-kind method that generates - from a single image - geometric facial details that are consistent with any desired target expression. The facial details are represented as a vertex displacement map and used then by a Neural Renderer to photo-realistically render novel images of any single image in any desired expression and view. The project website is: http://shahrukhathar.github.io/2020/12/14/FaceDet3D.html

Albert Pumarola, Enric Corona, Gerard Pons-Moll et al.

Neural rendering techniques combining machine learning with geometric reasoning have arisen as one of the most promising approaches for synthesizing novel views of a scene from a sparse set of images. Among these, stands out the Neural radiance fields (NeRF), which trains a deep network to map 5D input coordinates (representing spatial location and viewing direction) into a volume density and view-dependent emitted radiance. However, despite achieving an unprecedented level of photorealism on the generated images, NeRF is only applicable to static scenes, where the same spatial location can be queried from different images. In this paper we introduce D-NeRF, a method that extends neural radiance fields to a dynamic domain, allowing to reconstruct and render novel images of objects under rigid and non-rigid motions from a \emph{single} camera moving around the scene. For this purpose we consider time as an additional input to the system, and split the learning process in two main stages: one that encodes the scene into a canonical space and another that maps this canonical representation into the deformed scene at a particular time. Both mappings are simultaneously learned using fully-connected networks. Once the networks are trained, D-NeRF can render novel images, controlling both the camera view and the time variable, and thus, the object movement. We demonstrate the effectiveness of our approach on scenes with objects under rigid, articulated and non-rigid motions. Code, model weights and the dynamic scenes dataset will be released.

Albert Pumarola, Stefan Popov, Francesc Moreno-Noguer et al.

Flow-based generative models have highly desirable properties like exact log-likelihood evaluation and exact latent-variable inference, however they are still in their infancy and have not received as much attention as alternative generative models. In this paper, we introduce C-Flow, a novel conditioning scheme that brings normalizing flows to an entirely new scenario with great possibilities for multi-modal data modeling. C-Flow is based on a parallel sequence of invertible mappings in which a source flow guides the target flow at every step, enabling fine-grained control over the generation process. We also devise a new strategy to model unordered 3D point clouds that, in combination with the conditioning scheme, makes it possible to address 3D reconstruction from a single image and its inverse problem of rendering an image given a point cloud. We demonstrate our conditioning method to be very adaptable, being also applicable to image manipulation, style transfer and multi-modal image-to-image mapping in a diversity of domains, including RGB images, segmentation maps, and edge masks.

Albert Pumarola, Jordi Sanchez, Gary P. T. Choi et al.

Recent advances in 3D human shape estimation build upon parametric representations that model very well the shape of the naked body, but are not appropriate to represent the clothing geometry. In this paper, we present an approach to model dressed humans and predict their geometry from single images. We contribute in three fundamental aspects of the problem, namely, a new dataset, a novel shape parameterization algorithm and an end-to-end deep generative network for predicting shape. First, we present 3DPeople, a large-scale synthetic dataset with 2.5 Million photo-realistic images of 80 subjects performing 70 activities and wearing diverse outfits. Besides providing textured 3D meshes for clothes and body, we annotate the dataset with segmentation masks, skeletons, depth, normal maps and optical flow. All this together makes 3DPeople suitable for a plethora of tasks. We then represent the 3D shapes using 2D geometry images. To build these images we propose a novel spherical area-preserving parameterization algorithm based on the optimal mass transportation method. We show this approach to improve existing spherical maps which tend to shrink the elongated parts of the full body models such as the arms and legs, making the geometry images incomplete. Finally, we design a multi-resolution deep generative network that, given an input image of a dressed human, predicts his/her geometry image (and thus the clothed body shape) in an end-to-end manner. We obtain very promising results in jointly capturing body pose and clothing shape, both for synthetic validation and on the wild images.

Enric Corona, Albert Pumarola, Guillem Alenyà et al.

The problem of predicting human motion given a sequence of past observations is at the core of many applications in robotics and computer vision. Current state-of-the-art formulate this problem as a sequence-to-sequence task, in which a historical of 3D skeletons feeds a Recurrent Neural Network (RNN) that predicts future movements, typically in the order of 1 to 2 seconds. However, one aspect that has been obviated so far, is the fact that human motion is inherently driven by interactions with objects and/or other humans in the environment. In this paper, we explore this scenario using a novel context-aware motion prediction architecture. We use a semantic-graph model where the nodes parameterize the human and objects in the scene and the edges their mutual interactions. These interactions are iteratively learned through a graph attention layer, fed with the past observations, which now include both object and human body motions. Once this semantic graph is learned, we inject it to a standard RNN to predict future movements of the human/s and object/s. We consider two variants of our architecture, either freezing the contextual interactions in the future of updating them. A thorough evaluation in the "Whole-Body Human Motion Database" shows that in both cases, our context-aware networks clearly outperform baselines in which the context information is not considered.

Sergi Caelles, Albert Pumarola, Francesc Moreno-Noguer et al.

Learning descriptive spatio-temporal object models from data is paramount for the task of semi-supervised video object segmentation. Most existing approaches mainly rely on models that estimate the segmentation mask based on a reference mask at the first frame (aided sometimes by optical flow or the previous mask). These models, however, are prone to fail under rapid appearance changes or occlusions due to their limitations in modelling the temporal component. On the other hand, very recently, other approaches learned long-term features using a convolutional LSTM to leverage the information from all previous video frames. Even though these models achieve better temporal representations, they still have to be fine-tuned for every new video sequence. In this paper, we present an intermediate solution and devise a novel GAN architecture, FaSTGAN, to learn spatio-temporal object models over finite temporal windows. To achieve this, we concentrate all the heavy computational load to the training phase with two critics that enforce spatial and temporal mask consistency over the last K frames. Then at test time, we only use a relatively light regressor, which reduces the inference time considerably. As a result, our approach combines a high resiliency to sudden geometric and photometric object changes with efficiency at test time (no need for fine-tuning nor post-processing). We demonstrate that the accuracy of our method is on par with state-of-the-art techniques on the challenging YouTube-VOS and DAVIS datasets, while running at 32 fps, about 4x faster than the closest competitor.

Albert Pumarola, Antonio Agudo, Lorenzo Porzi et al.

We propose a method for predicting the 3D shape of a deformable surface from a single view. By contrast with previous approaches, we do not need a pre-registered template of the surface, and our method is robust to the lack of texture and partial occlusions. At the core of our approach is a {\it geometry-aware} deep architecture that tackles the problem as usually done in analytic solutions: first perform 2D detection of the mesh and then estimate a 3D shape that is geometrically consistent with the image. We train this architecture in an end-to-end manner using a large dataset of synthetic renderings of shapes under different levels of deformation, material properties, textures and lighting conditions. We evaluate our approach on a test split of this dataset and available real benchmarks, consistently improving state-of-the-art solutions with a significantly lower computational time.

Albert Pumarola, Antonio Agudo, Alberto Sanfeliu et al.

We present a novel approach for synthesizing photo-realistic images of people in arbitrary poses using generative adversarial learning. Given an input image of a person and a desired pose represented by a 2D skeleton, our model renders the image of the same person under the new pose, synthesizing novel views of the parts visible in the input image and hallucinating those that are not seen. This problem has recently been addressed in a supervised manner, i.e., during training the ground truth images under the new poses are given to the network. We go beyond these approaches by proposing a fully unsupervised strategy. We tackle this challenging scenario by splitting the problem into two principal subtasks. First, we consider a pose conditioned bidirectional generator that maps back the initially rendered image to the original pose, hence being directly comparable to the input image without the need to resort to any training image. Second, we devise a novel loss function that incorporates content and style terms, and aims at producing images of high perceptual quality. Extensive experiments conducted on the DeepFashion dataset demonstrate that the images rendered by our model are very close in appearance to those obtained by fully supervised approaches.

Albert Pumarola, Antonio Agudo, Aleix M. Martinez et al.

Recent advances in Generative Adversarial Networks (GANs) have shown impressive results for task of facial expression synthesis. The most successful architecture is StarGAN, that conditions GANs generation process with images of a specific domain, namely a set of images of persons sharing the same expression. While effective, this approach can only generate a discrete number of expressions, determined by the content of the dataset. To address this limitation, in this paper, we introduce a novel GAN conditioning scheme based on Action Units (AU) annotations, which describes in a continuous manifold the anatomical facial movements defining a human expression. Our approach allows controlling the magnitude of activation of each AU and combine several of them. Additionally, we propose a fully unsupervised strategy to train the model, that only requires images annotated with their activated AUs, and exploit attention mechanisms that make our network robust to changing backgrounds and lighting conditions. Extensive evaluation show that our approach goes beyond competing conditional generators both in the capability to synthesize a much wider range of expressions ruled by anatomically feasible muscle movements, as in the capacity of dealing with images in the wild.