Face recognition approaches often rely on equal image resolution for verification faces on two images. However, in practical applications, those image resolutions are usually not in the same range due to different image capture mechanisms or sources. In this work, we first analyze the impact of image resolutions on the face verification performance with a state-of-the-art face recognition model. For images, synthetically reduced to $5\, \times 5\, \mathrm{px}$ resolution, the verification performance drops from $99.23\%$ increasingly down to almost $55\%$. Especially, for cross-resolution image pairs (one high- and one low-resolution image), the verification accuracy decreases even further. We investigate this behavior more in-depth by looking at the feature distances for every 2-image test pair. To tackle this problem, we propose the following two methods: 1) Train a state-of-the-art face-recognition model straightforward with $50\%$ low-resolution images directly within each batch. \\ 2) Train a siamese-network structure and adding a cosine distance feature loss between high- and low-resolution features. Both methods show an improvement for cross-resolution scenarios and can increase the accuracy at very low resolution to approximately $70\%$. However, a disadvantage is that a specific model needs to be trained for every resolution-pair ...
Compared to color images captured by conventional RGB cameras, monochrome images usually have better signal-to-noise ratio (SNR) and richer textures due to its higher quantum efficiency. It is thus natural to apply a mono-color dual-camera system to restore color images with higher visual quality. In this paper, we propose a mono-color image enhancement algorithm that colorizes the monochrome image with the color one. Based on the assumption that adjacent structures with similar luminance values are likely to have similar colors, we first perform dense scribbling to assign colors to the monochrome pixels through block matching. Two types of outliers, including occlusion and color ambiguity, are detected and removed from the initial scribbles. We also introduce a sampling strategy to accelerate the scribbling process. Then, the dense scribbles are propagated to the entire image. To alleviate incorrect color propagation in the regions that have no color hints at all, we generate extra color seeds based on the existed scribbles to guide the propagation process. Experimental results show that, our algorithm can efficiently restore color images with higher SNR and richer details from the mono-color image pairs, and achieves good performance in solving the color bleeding problem.
Since photorealistic faces can be readily generated by facial manipulation technologies nowadays, potential malicious abuse of these technologies has drawn great concerns. Numerous deepfake detection methods are thus proposed. However, existing methods only focus on detecting one-step facial manipulation. As the emergence of easy-accessible facial editing applications, people can easily manipulate facial components using multi-step operations in a sequential manner. This new threat requires us to detect a sequence of facial manipulations, which is vital for both detecting deepfake media and recovering original faces afterwards. Motivated by this observation, we emphasize the need and propose a novel research problem called Detecting Sequential DeepFake Manipulation (Seq-DeepFake). Unlike the existing deepfake detection task only demanding a binary label prediction, detecting Seq-DeepFake manipulation requires correctly predicting a sequential vector of facial manipulation operations. To support a large-scale investigation, we construct the first Seq-DeepFake dataset, where face images are manipulated sequentially with corresponding annotations of sequential facial manipulation vectors. Based on this new dataset, we cast detecting Seq-DeepFake manipulation as a specific image-to-sequence (e.g. image captioning) task and propose a concise yet effective Seq-DeepFake Transformer (SeqFakeFormer). Moreover, we build a comprehensive benchmark and set up rigorous evaluation protocols and metrics for this new research problem. Extensive experiments demonstrate the effectiveness of SeqFakeFormer. Several valuable observations are also revealed to facilitate future research in broader deepfake detection problems.
Referring Image Segmentation (RIS) aims at segmenting the target object from an image referred by one given natural language expression. The diverse and flexible expressions as well as complex visual contents in the images raise the RIS model with higher demands for investigating fine-grained matching behaviors between words in expressions and objects presented in images. However, such matching behaviors are hard to be learned and captured when the visual cues of referents (i.e. referred objects) are insufficient, as the referents with weak visual cues tend to be easily confused by cluttered background at boundary or even overwhelmed by salient objects in the image. And the insufficient visual cues issue can not be handled by the cross-modal fusion mechanisms as done in previous work. In this paper, we tackle this problem from a novel perspective of enhancing the visual information for the referents by devising a Two-stage Visual cues enhancement Network (TV-Net), where a novel Retrieval and Enrichment Scheme (RES) and an Adaptive Multi-resolution feature Fusion (AMF) module are proposed. Through the two-stage enhancement, our proposed TV-Net enjoys better performances in learning fine-grained matching behaviors between the natural language expression and image, especially when the visual information of the referent is inadequate, thus produces better segmentation results. Extensive experiments are conducted to validate the effectiveness of the proposed method on the RIS task, with our proposed TV-Net surpassing the state-of-the-art approaches on four benchmark datasets.
A problem with synthetic aperture radar (SAR) is that due to the poor penetrating action of electromagnetic waves within solid bodies, the ability to observe through distributed targets is precluded. In this context, indeed, imaging is only possible on targets distribute on the scene surface. This work describes an imaging method based on the analysis of micro-motions present on volcanoes and generated by the underground Earth's heat. Processing the coherent vibrational information embedded on the single SAR image, in the single-look-complex configuration, the sound information is exploited, penetrating tomographic imaging over a depth of about 3 km from the Earth's surface. Measurement results are calculated by processing a SLC image from the COSMO-SkyMed Second Generation satellite constellation of the Vesuvius. Tomographic maps reveal the presence of the magma chamber, together with the main and the secondary volcanic conduits. This technique certainly paves the way for completely new exploitation of SAR images to scan inside the Earth's surface.
Visual-inertial localization is a key problem in computer vision and robotics applications such as virtual reality, self-driving cars, and aerial vehicles. The goal is to estimate an accurate pose of an object when either the environment or the dynamics are known. Recent methods directly regress the pose using convolutional and spatio-temporal networks. Absolute pose regression (APR) techniques predict the absolute camera pose from an image input in a known scene. Odometry methods perform relative pose regression (RPR) that predicts the relative pose from a known object dynamic (visual or inertial inputs). The localization task can be improved by retrieving information of both data sources for a cross-modal setup, which is a challenging problem due to contradictory tasks. In this work, we conduct a benchmark to evaluate deep multimodal fusion based on PGO and attention networks. Auxiliary and Bayesian learning are integrated for the APR task. We show accuracy improvements for the RPR-aided APR task and for the RPR-RPR task for aerial vehicles and hand-held devices. We conduct experiments on the EuRoC MAV and PennCOSYVIO datasets, and record a novel industry dataset.
The recent advances in image transformers have shown impressive results and have largely closed the gap between traditional CNN architectures. The standard procedure is to train on large datasets like ImageNet-21k and then finetune on ImageNet-1k. After finetuning, researches will often consider the transfer learning performance on smaller datasets such as CIFAR-10/100 but have left out Tiny ImageNet. This paper offers an update on vision transformers' performance on Tiny ImageNet. I include Vision Transformer (ViT) , Data Efficient Image Transformer (DeiT), Class Attention in Image Transformer (CaiT), and Swin Transformers. In addition, Swin Transformers beats the current state-of-the-art result with a validation accuracy of 91.35%. Code is available here: https://github.com/ehuynh1106/TinyImageNet-Transformers
In this paper, we propose an object-based camera pose estimation from a single RGB image and a pre-built map of objects, represented with ellipsoidal models. We show that contrary to point correspondences, the definition of a cost function characterizing the projection of a 3D object onto a 2D object detection is not straightforward. We develop an ellipse-ellipse cost based on level sets sampling, demonstrate its nice properties for handling partially visible objects and compare its performance with other common metrics. Finally, we show that the use of a predictive uncertainty on the detected ellipses allows a fair weighting of the contribution of the correspondences which improves the computed pose. The code is released at https://gitlab.inria.fr/tangram/level-set-based-camera-pose-estimation.
The Scene Graph Generation (SGG) task aims to detect all the objects and their pairwise visual relationships in a given image. Although SGG has achieved remarkable progress over the last few years, almost all existing SGG models follow the same training paradigm: they treat both object and predicate classification in SGG as a single-label classification problem, and the ground-truths are one-hot target labels. However, this prevalent training paradigm has overlooked two characteristics of current SGG datasets: 1) For positive samples, some specific subject-object instances may have multiple reasonable predicates. 2) For negative samples, there are numerous missing annotations. Regardless of the two characteristics, SGG models are easy to be confused and make wrong predictions. To this end, we propose a novel model-agnostic Label Semantic Knowledge Distillation (LS-KD) for unbiased SGG. Specifically, LS-KD dynamically generates a soft label for each subject-object instance by fusing a predicted Label Semantic Distribution (LSD) with its original one-hot target label. LSD reflects the correlations between this instance and multiple predicate categories. Meanwhile, we propose two different strategies to predict LSD: iterative self-KD and synchronous self-KD. Extensive ablations and results on three SGG tasks have attested to the superiority and generality of our proposed LS-KD, which can consistently achieve decent trade-off performance between different predicate categories.
Image Signal Processor (ISP) is a crucial component in digital cameras that transforms sensor signals into images for us to perceive and understand. Existing ISP designs always adopt a fixed architecture, e.g., several sequential modules connected in a rigid order. Such a fixed ISP architecture may be suboptimal for real-world applications, where camera sensors, scenes and tasks are diverse. In this study, we propose a novel Reconfigurable ISP (ReconfigISP) whose architecture and parameters can be automatically tailored to specific data and tasks. In particular, we implement several ISP modules, and enable backpropagation for each module by training a differentiable proxy, hence allowing us to leverage the popular differentiable neural architecture search and effectively search for the optimal ISP architecture. A proxy tuning mechanism is adopted to maintain the accuracy of proxy networks in all cases. Extensive experiments conducted on image restoration and object detection, with different sensors, light conditions and efficiency constraints, validate the effectiveness of ReconfigISP. Only hundreds of parameters need tuning for every task.