Sign languages are visual languages, with vocabularies as rich as their spoken language counterparts. However, current deep-learning based Sign Language Production (SLP) models produce under-articulated skeleton pose sequences from constrained vocabularies and this limits applicability. To be understandable and accepted by the deaf, an automatic SLP system must be able to generate co-articulated photo-realistic signing sequences for large domains of discourse. In this work, we tackle large-scale SLP by learning to co-articulate between dictionary signs, a method capable of producing smooth signing while scaling to unconstrained domains of discourse. To learn sign co-articulation, we propose a novel Frame Selection Network (FS-Net) that improves the temporal alignment of interpolated dictionary signs to continuous signing sequences. Additionally, we propose SignGAN, a pose-conditioned human synthesis model that produces photo-realistic sign language videos direct from skeleton pose. We propose a novel keypoint-based loss function which improves the quality of synthesized hand images. We evaluate our SLP model on the large-scale meineDGS (mDGS) corpus, conducting extensive user evaluation showing our FS-Net approach improves co-articulation of interpolated dictionary signs. Additionally, we show that SignGAN significantly outperforms all baseline methods for quantitative metrics, human perceptual studies and native deaf signer comprehension.
We examined the feasibility of generative adversarial networks (GANs) to generate photo-realistic images from LiDAR point clouds. For this purpose, we created a dataset of point cloud image pairs and trained the GAN to predict photorealistic images from LiDAR point clouds containing reflectance and distance information. Our models learned how to predict realistically looking images from just point cloud data, even images with black cars. Black cars are difficult to detect directly from point clouds because of their low level of reflectivity. This approach might be used in the future to perform visual object recognition on photorealistic images generated from LiDAR point clouds. In addition to the conventional LiDAR system, a second system that generates photorealistic images from LiDAR point clouds would run simultaneously for visual object recognition in real-time. In this way, we might preserve the supremacy of LiDAR and benefit from using photo-realistic images for visual object recognition without the usage of any camera. In addition, this approach could be used to colorize point clouds without the usage of any camera images.
Normalizing flow models using invertible neural networks (INN) have been widely investigated for successful generative image super-resolution (SR) by learning the transformation between the normal distribution of latent variable $z$ and the conditional distribution of high-resolution (HR) images gave a low-resolution (LR) input. Recently, image rescaling models like IRN utilize the bidirectional nature of INN to push the performance limit of image upscaling by optimizing the downscaling and upscaling steps jointly. While the random sampling of latent variable $z$ is useful in generating diverse photo-realistic images, it is not desirable for image rescaling when accurate restoration of the HR image is more important. Hence, in places of random sampling of $z$, we propose auxiliary encoding modules to further push the limit of image rescaling performance. Two options to store the encoded latent variables in downscaled LR images, both readily supported in existing image file format, are proposed. One is saved as the alpha-channel, the other is saved as meta-data in the image header, and the corresponding modules are denoted as suffixes -A and -M respectively. Optimal network architectural changes are investigated for both options to demonstrate their effectiveness in raising the rescaling performance limit on different baseline models including IRN and DLV-IRN.
In this paper, we leverage CLIP for zero-shot sketch based image retrieval (ZS-SBIR). We are largely inspired by recent advances on foundation models and the unparalleled generalisation ability they seem to offer, but for the first time tailor it to benefit the sketch community. We put forward novel designs on how best to achieve this synergy, for both the category setting and the fine-grained setting ("all"). At the very core of our solution is a prompt learning setup. First we show just via factoring in sketch-specific prompts, we already have a category-level ZS-SBIR system that overshoots all prior arts, by a large margin (24.8%) - a great testimony on studying the CLIP and ZS-SBIR synergy. Moving onto the fine-grained setup is however trickier, and requires a deeper dive into this synergy. For that, we come up with two specific designs to tackle the fine-grained matching nature of the problem: (i) an additional regularisation loss to ensure the relative separation between sketches and photos is uniform across categories, which is not the case for the gold standard standalone triplet loss, and (ii) a clever patch shuffling technique to help establishing instance-level structural correspondences between sketch-photo pairs. With these designs, we again observe significant performance gains in the region of 26.9% over previous state-of-the-art. The take-home message, if any, is the proposed CLIP and prompt learning paradigm carries great promise in tackling other sketch-related tasks (not limited to ZS-SBIR) where data scarcity remains a great challenge. Project page: https://aneeshan95.github.io/Sketch_LVM/
In this work we propose a photorealistic style transfer method for image and video that is based on vision science principles and on a recent mathematical formulation for the deterministic decoupling of sample statistics. The novel aspects of our approach include matching decoupled moments of higher order than in common style transfer approaches, and matching a descriptor of the power spectrum so as to characterize and transfer diffusion effects between source and target, which is something that has not been considered before in the literature. The results are of high visual quality, without spatio-temporal artifacts, and validation tests in the form of observer preference experiments show that our method compares very well with the state-of-the-art. The computational complexity of the algorithm is low, and we propose a numerical implementation that is amenable for real-time video application. Finally, another contribution of our work is to point out that current deep learning approaches for photorealistic style transfer don't really achieve photorealistic quality outside of limited examples, because the results too often show unacceptable visual artifacts.
The problem of spurious correlations (SCs) arises when a classifier relies on non-predictive features that happen to be correlated with the labels in the training data. For example, a classifier may misclassify dog breeds based on the background of dog images. This happens when the backgrounds are correlated with other breeds in the training data, leading to misclassifications during test time. Previous SC benchmark datasets suffer from varying issues, e.g., over-saturation or only containing one-to-one (O2O) SCs, but no many-to-many (M2M) SCs arising between groups of spurious attributes and classes. In this paper, we present Spawrious-{O2O, M2M}-{Easy, Medium, Hard}, an image classification benchmark suite containing spurious correlations among different dog breeds and background locations. To create this dataset, we employ a text-to-image model to generate photo-realistic images, and an image captioning model to filter out unsuitable ones. The resulting dataset is of high quality, containing approximately 152,000 images. Our experimental results demonstrate that state-of-the-art group robustness methods struggle with Spawrious, most notably on the Hard-splits with $<60\%$ accuracy. By examining model misclassifications, we detect reliances on spurious backgrounds, demonstrating that our dataset provides a significant challenge to drive future research.
While recent methods for motion and stereo estimation recover an unprecedented amount of details, such highly detailed structures are neither adequately reflected in the data of existing benchmarks nor their evaluation methodology. Hence, we introduce Spring $-$ a large, high-resolution, high-detail, computer-generated benchmark for scene flow, optical flow, and stereo. Based on rendered scenes from the open-source Blender movie "Spring", it provides photo-realistic HD datasets with state-of-the-art visual effects and ground truth training data. Furthermore, we provide a website to upload, analyze and compare results. Using a novel evaluation methodology based on a super-resolved UHD ground truth, our Spring benchmark can assess the quality of fine structures and provides further detailed performance statistics on different image regions. Regarding the number of ground truth frames, Spring is 60$\times$ larger than the only scene flow benchmark, KITTI 2015, and 15$\times$ larger than the well-established MPI Sintel optical flow benchmark. Initial results for recent methods on our benchmark show that estimating fine details is indeed challenging, as their accuracy leaves significant room for improvement. The Spring benchmark and the corresponding datasets are available at http://spring-benchmark.org.
Lensless imaging protects visual privacy by capturing heavily blurred images that are imperceptible for humans to recognize the subject but contain enough information for machines to infer information. Unfortunately, protecting visual privacy comes with a reduction in recognition accuracy and vice versa. We propose a learnable lensless imaging framework that protects visual privacy while maintaining recognition accuracy. To make captured images imperceptible to humans, we designed several loss functions based on total variation, invertibility, and the restricted isometry property. We studied the effect of privacy protection with blurriness on the identification of personal identity via a quantitative method based on a subjective evaluation. Moreover, we validate our simulation by implementing a hardware realization of lensless imaging with photo-lithographically printed masks.
For few-shot learning, it is still a critical challenge to realize photo-realistic face visually dubbing on high-resolution videos. Previous works fail to generate high-fidelity dubbing results. To address the above problem, this paper proposes a Deformation Inpainting Network (DINet) for high-resolution face visually dubbing. Different from previous works relying on multiple up-sample layers to directly generate pixels from latent embeddings, DINet performs spatial deformation on feature maps of reference images to better preserve high-frequency textural details. Specifically, DINet consists of one deformation part and one inpainting part. In the first part, five reference facial images adaptively perform spatial deformation to create deformed feature maps encoding mouth shapes at each frame, in order to align with the input driving audio and also the head poses of the input source images. In the second part, to produce face visually dubbing, a feature decoder is responsible for adaptively incorporating mouth movements from the deformed feature maps and other attributes (i.e., head pose and upper facial expression) from the source feature maps together. Finally, DINet achieves face visually dubbing with rich textural details. We conduct qualitative and quantitative comparisons to validate our DINet on high-resolution videos. The experimental results show that our method outperforms state-of-the-art works.