Faithful real-time facial animation is essential for avatar-mediated telepresence in Virtual Reality (VR). To emulate authentic communication, avatar animation needs to be efficient and accurate: able to capture both extreme and subtle expressions within a few milliseconds to sustain the rhythm of natural conversations. The oblique and incomplete views of the face, variability in the donning of headsets, and illumination variation due to the environment are some of the unique challenges in generalization to unseen faces. In this paper, we present a method that can animate a photorealistic avatar in realtime from head-mounted cameras (HMCs) on a consumer VR headset. We present a self-supervised learning approach, based on a cross-view reconstruction objective, that enables generalization to unseen users. We present a lightweight expression calibration mechanism that increases accuracy with minimal additional cost to run-time efficiency. We present an improved parameterization for precise ground-truth generation that provides robustness to environmental variation. The resulting system produces accurate facial animation for unseen users wearing VR headsets in realtime. We compare our approach to prior face-encoding methods demonstrating significant improvements in both quantitative metrics and qualitative results.
论文检索
输入标题、作者或关键词，从 2,578 篇学术成果中精准定位
Gradient-based optimization is now ubiquitous across graphics, but unfortunately can not be applied to problems with undefined or zero gradients. To circumvent this issue, the loss function can be manually replaced by a "surrogate" that has similar minima but is differentiable. Our proposed framework, ZeroGrads, automates this process by learning a neural approximation of the objective function, which in turn can be used to differentiate through arbitrary black-box graphics pipelines. We train the surrogate on an actively smoothed version of the objective and encourage locality, focusing the surrogate's capacity on what matters at the current training episode. The fitting is performed online, alongside the parameter optimization, and self-supervised, without pre-computed data or pre-trained models. As sampling the objective is expensive (it requires a full rendering or simulator run), we devise an efficient sampling scheme that allows for tractable run-times and competitive performance at little overhead. We demonstrate optimizing diverse non-convex, non-differentiable black-box problems in graphics, such as visibility in rendering, discrete parameter spaces in procedural modelling or optimal control in physics-driven animation. In contrast to other derivative-free algorithms, our approach scales well to higher dimensions, which we demonstrate on problems with up to 35k interlinked variables.
Misfocus is ubiquitous for almost all video producers, degrading video quality and often causing expensive delays and reshoots. Current autofocus (AF) systems are vulnerable to sudden disturbances such as subject movement or lighting changes commonly present in real-world and on-set conditions. Single image defocus deblurring methods are temporally unstable when applied to videos and cannot recover details obscured by temporally varying defocus blur. In this paper, we present an end-to-end solution that allows users to correct misfocus during post-processing. Our method generates and parameterizes defocused videos into sharp layered neural atlases and propagates consistent focus tracking back to the video frames. We introduce a novel differentiable disk blur layer for more accurate point spread function (PSF) simulation, coupled with a circle of confusion (COC) map estimation module with knowledge transferred from the current single image defocus deblurring (SIDD) networks. Our pipeline offers consistent, sharp video reconstruction and effective subject-focus correction and tracking directly on the generated atlases. Furthermore, by adopting our approach, we achieve comparable results to the state-of-the-art optical flow estimation approach from defocus videos.
Deoccluding the hidden portions of objects in a scene is a formidable task, particularly when addressing real-world scenes. In this paper, we present a new self-supervised PArallel visible-to-COmplete diffusion framework, named PACO, a foundation model for object-level scene deocclusion. Leveraging the rich prior of pre-trained models, we first design the parallel variational autoencoder, which produces a full-view feature map that simultaneously encodes multiple complete objects, and the visible-to-complete latent generator, which learns to implicitly predict the full-view feature map from partial-view feature map and text prompts extracted from the incomplete objects in the input image. To train PACO, we create a large-scale dataset with 500k samples to enable self-supervised learning, avoiding tedious annotations of the amodal masks and occluded regions. At inference, we devise a layer-wise deocclusion strategy to improve efficiency while maintaining the deocclusion quality. Extensive experiments on COCOA and various real-world scenes demonstrate the superior capability of PACO for scene deocclusion, surpassing the state of the arts by a large margin. Our method can also be extended to cross-domain scenes and novel categories that are not covered by the training set. Further, we demonstrate the deocclusion applicability of PACO in single-view 3D scene reconstruction and object recomposition. Project page: https://liuzhengzhe.github.io/Deocclude-Any-Object.github.io/.
We delve into the physics-informed neural reconstruction of smoke and obstacles through sparse-view RGB videos, tackling challenges arising from limited observation of complex dynamics. Existing physics-informed neural networks often emphasize short-term physics constraints, leaving the proper preservation of long-term conservation less explored. We introduce Neural Characteristic Trajectory Fields, a novel representation utilizing Eulerian neural fields to implicitly model Lagrangian fluid trajectories. This topology-free, auto-differentiable representation facilitates efficient flow map calculations between arbitrary frames as well as efficient velocity extraction via auto-differentiation. Consequently, it enables end-to-end supervision covering long-term conservation and short-term physics priors. Building on the representation, we propose physics-informed trajectory learning and integration into NeRF-based scene reconstruction. We enable advanced obstacle handling through self-supervised scene decomposition and seamless integrated boundary constraints. Our results showcase the ability to overcome challenges like occlusion uncertainty, density-color ambiguity, and static-dynamic entanglements. Code and sample tests are at https://github.com/19reborn/PICT_smoke.
In this paper, we introduce the Volumetric Relightable Morphable Model (VRMM), a novel volumetric and parametric facial prior for 3D face modeling. While recent volumetric prior models offer improvements over traditional methods like 3D Morphable Models (3DMMs), they face challenges in model learning and personalized reconstructions. Our VRMM overcomes these by employing a novel training framework that efficiently disentangles and encodes latent spaces of identity, expression, and lighting into low-dimensional representations. This framework, designed with self-supervised learning, significantly reduces the constraints for training data, making it more feasible in practice. The learned VRMM offers relighting capabilities and encompasses a comprehensive range of expressions. We demonstrate the versatility and effectiveness of VRMM through various applications like avatar generation, facial reconstruction, and animation. Additionally, we address the common issue of overfitting in generative volumetric models with a novel prior-preserving personalization framework based on VRMM. Such an approach enables high-quality 3D face reconstruction from even a single portrait input. Our experiments showcase the potential of VRMM to significantly enhance the field of 3D face modeling.
We propose a method to decompose a single eye region image in the wild into albedo, shading, specular, normal and illumination. This inverse rendering problem is particularly challenging due to inherent ambiguities and complex properties of the natural eye region. To address this problem, first we construct a synthetic eye region dataset with rich diversity. Then we propose a synthetic to real adaptation framework to leverage the supervision signals from synthetic data to guide the direction of self-supervised learning. We design region-aware self-supervised losses based on image formation and eye region intrinsic properties, which can refine each predicted component by mutual learning and reduce the artifacts caused by ambiguities of natural eye images. Particularly, we address the demanding problem of specularity removal in the eye region. We show high-quality inverse rendering results of our method and demonstrate its use for a number of applications.
We present a simple, self-supervised approach to the Tracking Any Point (TAP) problem. We train a global matching transformer to find cycle consistent tracks through video via contrastive random walks, using the transformer's attention-based global matching to define the transition matrices for a random walk on a space-time graph. The ability to perform "all pairs" comparisons between points allows the model to obtain high spatial precision and to obtain a strong contrastive learning signal, while avoiding the complexities of recent approaches (such as coarse-to-fine matching). To do this, we propose a number of design decisions that allow global matching architectures to be trained through self-supervision using cycle consistency. For example, we identify that transformer-based methods are sensitive to shortcut solutions, and propose a data augmentation scheme to address them. Our method achieves strong performance on the TapVid benchmarks, outperforming previous self-supervised tracking methods, such as DIFT, and is competitive with several supervised methods.
This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the state-of-the-art method of CASA, where sequences of 3D skeleton coordinates are taken directly as input, our key idea is to use sequences of 2D skeleton heatmaps as input. Unlike CASA which performs self-attention in the temporal domain only, we feed 2D skeleton heatmaps to a video transformer which performs self-attention both in the spatial and temporal domains for extracting effective spatiotemporal and contextual features. In addition, we introduce simple heatmap augmentation techniques based on 2D skeletons for self-supervised learning. Despite the lack of 3D information, our approach achieves not only higher accuracy but also better robustness against missing and noisy keypoints than CASA. Furthermore, extensive evaluations on three public datasets, i.e., Penn Action, IKEA ASM, and H2O, demonstrate that our approach outperforms previous methods in different fine-grained human activity understanding tasks. Finally, fusing 2D skeleton heatmaps with RGB videos yields the state-of-the-art on all metrics and datasets. To our best knowledge, our work is the first to utilize 2D skeleton heatmap inputs and the first to explore multi-modality fusion for temporal video alignment.
On Learning Discriminative Features from Synthesized Data for Self-Supervised Fine-Grained Visual Recognition
PDF ↗Self-Supervised Learning (SSL) has become a prominent approach for acquiring visual representations across various tasks, yet its application in fine-grained visual recognition (FGVR) is challenged by the intricate task of distinguishing subtle differences between categories. To overcome this, we introduce an novel strategy that boosts SSL's ability to extract critical discriminative features vital for FGVR. This approach creates synthesized data pairs to guide the model to focus on discriminative features critical for FGVR during SSL. We start by identifying non-discriminative features using two main criteria: features with low variance that fail to effectively separate data and those deemed less important by Grad-CAM induced from the SSL loss. We then introduce perturbations to these non-discriminative features while preserving discriminative ones. A decoder is employed to reconstruct images from both perturbed and original feature vectors to create data pairs. An encoder is trained on such generated data pairs to become invariant to variations in non-discriminative dimensions while focusing on discriminative features, thereby improving the model's performance in FGVR tasks. We demonstrate the promising FGVR performance of the proposed approach through extensive evaluation on a wide variety of datasets.
The task of video copy localization aims at finding the start and end timestamps of all copied segments within a pair of untrimmed videos. Recent approaches usually extract frame-level features and generate a frame-to-frame similarity map for the video pair. Learned detectors are used to identify distinctive patterns in the similarity map to localize the copied segments. There are two major limitations associated with these methods. First, they often rely on a single feature for each frame, which is inadequate in capturing local information for typical scenarios in video copy editing, such as picture-in-picture cases. Second, the training of the detectors requires a significant amount of human annotated data, which is highly expensive and time-consuming to acquire. In this paper, we propose a self-supervised video copy localization framework to tackle these issues. We incorporate a Regional Token into the Vision Transformer, which learns to focus on local regions within each frame using an asymmetric training procedure. A novel strategy that leverages the Transitivity Property is proposed to generate copied video pairs automatically, which facilitates the training of the detector. Extensive experiments and visualizations demonstrate the effectiveness of the proposed approach, which is able to outperform the state-of-the-art without using any human annotated data.
Self-supervised learning (SSL) is a prevalent approach for encoding data representations. Using a pre-trained SSL image encoder and subsequently training a downstream classifier, impressive performance can be achieved on various tasks with very little labeled data. The growing adoption of SSL has led to an increase in security research on SSL encoders and associated Trojan attacks. Trojan attacks embedded in SSL encoders can operate covertly, spreading across multiple users and devices. The presence of backdoor behavior in Trojaned encoders can inadvertently be inherited by downstream classifiers, making it even more difficult to detect and mitigate the threat. Although current Trojan detection methods in supervised learning can potentially safeguard SSL downstream classifiers, identifying and addressing triggers in the SSL encoder before its widespread dissemination is a challenging task. This challenge arises because downstream tasks might be unknown, dataset labels may be unavailable, and the original unlabeled training dataset might be inaccessible during Trojan detection in SSL encoders. We introduce \textbf{SSL-Cleanse} as a solution to identify and mitigate backdoor threats in SSL encoders. We evaluated SSL-Cleanse on various datasets using 1200 encoders, achieving an average detection success rate of $82.2\%$ on ImageNet-100. After mitigating backdoors, on average, backdoored encoders achieve $0.3\%$ attack success rate without great accuracy loss, proving the effectiveness of SSL-Cleanse.
With the emergent attentive property of self-supervised Vision Transformer (ViT), Normalized Cuts (NCut) has resurfaced as a powerful tool for unsupervised dense prediction. However, the pre-trained ViT backbone (e.g., DINO) is frozen in existing methods, which makes the feature extractor suboptimal for dense prediction tasks. In this paper, we propose using Differentiable Normalized Cuts for self-supervised dense feature learning that can improve the dense prediction capability of existing pre-trained models. First, we review an efficient gradient formulation for the classical NCut algorithm. This formulation only leverages matrices computed and stored in the forward pass, making the backward pass highly efficient. Second, with NCut gradients in hand, we design a self-supervised dense feature learning architecture to finetune pre-trained models. Given two random augmented crops of an image, the architecture performs RoIAlign and NCut to generate two foreground masks of their overlapping region. Last, we propose a mask-consistency loss to back-propagate through NCut and RoIAlign for model training. Experiments show that our framework generalizes to various pre-training methods (DINO, MoCo and MAE), network configurations (ResNet, ViT-S and ViT-B), and tasks (unsupervised saliency detection, object discovery and semantic correspondence). Moreover, we achieved state-of-the-art results on unsupervised dense prediction benchmarks.
Developing self-supervised learning (SSL) models that can learn universal and transferable representations of H&E gigapixel whole-slide images (WSIs) is becoming increasingly valuable in computational pathology. These models hold the potential to advance critical tasks such as few-shot classification, slide retrieval, and patient stratification. Existing approaches for slide representation learning extend the principles of SSL from small images (e.g., 224 x 224 patches) to entire slides, usually by aligning two different augmentations (or \emph{views}) of the slide. Yet the resulting representation remains constrained by the limited clinical and biological relevance of the views. Instead, we postulate that slides stained with multiple markers, such as immunohistochemistry or special stains, can be seen as different views of the same tissue and can constitute a rich task-agnostic training signal. To this end, we introduce MADELEINE, a multimodal pretraining strategy for slide representation learning. MADELEINE is trained with a dual global-local cross-stain alignment objective on large cohorts of breast cancer samples (N=4,211 WSIs across five stains) and kidney transplant samples (N=12,070 WSIs across four stains). We demonstrate the superior quality of slide representations learned by MADELEINE on various downstream evaluations, ranging from morphological and molecular classification to prognostic prediction, on a total of 21 tasks using 7,299 WSIs from multiple medical centers. Code will be released upon acceptance.
This paper explores self-supervised disentangled representation learning within sequential data, focusing on untangling time-independent and time-varying factors in videos. We propose a new model that explicitly accounts for the causal relationship between the static/dynamic variables and improves model expressivity through additional Normalizing Flows. A formal definition of the factors is proposed. This formalism leads to the derivation of sufficient conditions under which the ground truth factors can be identified, and introduction of a novel theoretically grounded disentanglement constraint that can be directly and efficiently incorporated into the framework. The experiments show that the proposed approach outperforms previous SOTA techniques which generalize poorly in more realistic scenarios where the dynamics of a scene are influenced by the content.
We introduce a novel neural volumetric pose feature, termed PoseMap, designed to enhance camera localization by encapsulating the information between images and the associated camera poses. Our framework leverages an Absolute Pose Regression (APR) architecture, together with an augmented NeRF module. This integration not only facilitates the generation of novel views to enrich the training dataset but also enables the learning of effective pose features. Additionally, we extend our architecture for self-supervised online alignment, allowing our method to be used and fine-tuned for unlabelled images within a unified framework. Experiments demonstrate that our method achieves 14.28% and 20.51% performance gain on average in indoor and outdoor benchmark scenes, outperforming existing APR methods with state-of-the-art accuracy.
Images and structured tables are essential parts of real-world databases. Though tabular-image representation learning is promising to create new insights, it remains a challenging task, as tabular data is typically heterogeneous and incomplete, presenting significant modality disparities with images. Earlier works have mainly focused on simple modality fusion strategies in complete data scenarios, without considering the missing data issue, and thus are limited in practice. In this paper, we propose TIP, a novel tabular-image pre-training framework for learning multimodal representations robust to incomplete tabular data. Specifically, TIP investigates a novel self-supervised learning (SSL) strategy, including a masked tabular reconstruction task for tackling data missingness, and image-tabular matching and contrastive learning objectives to capture multimodal information. Moreover, TIP proposes a versatile tabular encoder tailored for incomplete, heterogeneous tabular data and a multimodal interaction module for inter-modality representation learning. Experiments are performed on downstream multimodal classification tasks using both natural and medical image datasets. The results show that TIP outperforms state-of-the-art supervised/SSL image/multimodal algorithms in both complete and incomplete data scenarios. Our code will be available at https://github.com/anonymous.
Semi-supervised learning is a learning method that uses both labeled and unlabeled samples to improve the performance of the model while reducing labeling costs. When there were tens to hundreds of labeled samples, semi-supervised learning methods showed good performance, but most of them showed poor performance when only a small number of labeled samples were given. In this paper, we focus on challenging label-scarce environments, where there are only a few labeled samples per class. Our proposed model, ExMatch, is designed to obtain reliable information from unlabeled samples using self-supervised models and utilize it for semi-supervised learning. In the training process, ExMatch guides the model to maintain an appropriate distribution and resist learning from incorrect pseudo-labels based on the information from self-supervised models and its own model. ExMatch shows very stable training progress and the state-of-the-art performances on multiple benchmark datasets. In extremely label-scare situations, performances are improved by about 5% to 21% for CIFAR-10/100 and SVHN. ExMatch also demonstrates significant performance improvements in high-resolution and large-scale dataset such as STL-10, Tiny-ImageNet, and ImageNet.
Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a phenomenon where the trained model captures only a limited portion of the information from the input data while overlooking other potentially valuable content. This issue often leads to indistinguishable representations for visually similar but semantically different inputs, adversely affecting downstream task performance, particularly those requiring rigorous semantic comprehension. To address this challenge, we propose a novel model-agnostic Multistage Contrastive Learning (MCL) framework. Unlike standard contrastive learning which inherently captures one single biased feature distribution, MCL progressively learns previously unlearned features through feature-aware negative sampling at each stage, where the negative samples of an anchor are exclusively selected from the cluster it was assigned to in preceding stages. Meanwhile, MCL preserves the previously well-learned features by cross-stage representation integration, integrating features across all stages to form final representations. Our comprehensive evaluation demonstrates MCL's effectiveness and superiority across both unimodal and multimodal contrastive learning, spanning a range of model architectures from ResNet to Vision Transformers (ViT). Remarkably, in tasks where the original CLIP model has shown limitations, MCL dramatically enhances performance, with improvements up to threefold on specific attributes in the recently proposed MMVP benchmark. Codes can be found in the supplementary materials.
Earth Observation (EO) presents a unique opportunity to explore self-supervised multimodal learning, given its access to vast and diverse data captured by various sensors. However, current multimodal EO datasets and models often consider modalities from a single data type, either mono-date images or time series, which limits their expressivity. We introduce OmniSat, a novel architecture that exploits the natural alignment between multiple EO modalities to learn expressive multimodal representations without labels. We augment an existing dataset with new modalities to demonstrate the advantages of combining modalities of different natures. We evaluate OmniSat and various state-of-the-art approaches on two relevant downstream tasks: forestry and land cover classification. Our results show that OmniSat can learn rich representations in an unsupervised manner, leading to performance improvements in the semi- and fully-supervised settings, even when only one modality is available at inference. Our code, weights, and dataset are available at https://github.com/gastruc/OmniSat.