Fréderic Dufaux

Marouane Tliba, Aladine Chetouani, Giuseppe Valenzise et al.

Following the advent of immersive technologies and the increasing interest in representing interactive geometrical format, 3D Point Clouds (PC) have emerged as a promising solution and effective means to display 3D visual information. In addition to other challenges in immersive applications, objective and subjective quality assessments of compressed 3D content remain open problems and an area of research interest. Yet most of the efforts in the research area ignore the local geometrical structures between points representation. In this paper, we overcome this limitation by introducing a novel and efficient objective metric for Point Clouds Quality Assessment, by learning local intrinsic dependencies using Graph Neural Network (GNN). To evaluate the performance of our method, two well-known datasets have been used. The results demonstrate the effectiveness and reliability of our solution compared to state-of-the-art metrics.

Marouane Tliba, Aladine Chetouani, Giuseppe Valenzise et al.

With the increased interest in immersive experiences, point cloud came to birth and was widely adopted as the first choice to represent 3D media. Besides several distortions that could affect the 3D content spanning from acquisition to rendering, efficient transmission of such volumetric content over traditional communication systems stands at the expense of the delivered perceptual quality. To estimate the magnitude of such degradation, employing quality metrics became an inevitable solution. In this work, we propose a novel deep-based no-reference quality metric that operates directly on the whole point cloud without requiring extensive pre-processing, enabling real-time evaluation over both transmission and rendering levels. To do so, we use a novel model design consisting primarily of cross and self-attention layers, in order to learn the best set of local semantic affinities while keeping the best combination of geometry and color information in multiple levels from basic features extraction to deep representation modeling.

Maurice Quach, Aladine Chetouani, Giuseppe Valenzise et al.

Point clouds are essential for storage and transmission of 3D content. As they can entail significant volumes of data, point cloud compression is crucial for practical usage. Recently, point cloud geometry compression approaches based on deep neural networks have been explored. In this paper, we evaluate the ability to predict perceptual quality of typical voxel-based loss functions employed to train these networks. We find that the commonly used focal loss and weighted binary cross entropy are poorly correlated with human perception. We thus propose a perceptual loss function for 3D point clouds which outperforms existing loss functions on the ICIP2020 subjective dataset. In addition, we propose a novel truncated distance field voxel grid representation and find that it leads to sparser latent spaces and loss functions that are more correlated with perceived visual quality compared to a binary representation. The source code is available at https://github.com/mauriceqch/2021_pc_perceptual_loss.

Maurice Quach, Giuseppe Valenzise, Frederic Dufaux

Point clouds have been recognized as a crucial data structure for 3D content and are essential in a number of applications such as virtual and mixed reality, autonomous driving, cultural heritage, etc. In this paper, we propose a set of contributions to improve deep point cloud compression, i.e.: using a scale hyperprior model for entropy coding; employing deeper transforms; a different balancing weight in the focal loss; optimal thresholding for decoding; and sequential model training. In addition, we present an extensive ablation study on the impact of each of these factors, in order to provide a better understanding about why they improve RD performance. An optimal combination of the proposed improvements achieves BD-PSNR gains over G-PCC trisoup and octree of 5.50 (6.48) dB and 6.84 (5.95) dB, respectively, when using the point-to-point (point-to-plane) metric. Code is available at https://github.com/mauriceqch/pcc_geo_cnn_v2 .

Théo Gigant, Camille Guinaudeau, Frédéric Dufaux

Vision-Language Models (VLMs) can process visual and textual information in multiple formats: texts, images, interleaved texts and images, or even hour-long videos. In this work, we conduct fine-grained quantitative and qualitative analyses of automatic summarization of multimodal presentations using VLMs with various representations as input. From these experiments, we suggest cost-effective strategies for generating summaries from text-heavy multimodal documents under different input-length budgets using VLMs. We show that slides extracted from the video stream can be beneficially used as input against the raw video, and that a structured representation from interleaved slides and transcript provides the best performance. Finally, we reflect and comment on the nature of cross-modal interactions in multimodal presentations and share suggestions to improve the capabilities of VLMs to understand documents of this nature.

Ruituo Wu, Yang Chen, Jian Xiao et al.

Cooperation between temporal convolutional networks (TCN) and graph convolutional networks (GCN) as a processing module has shown promising results in skeleton-based video anomaly detection (SVAD). However, to maintain a lightweight model with low computational and storage complexity, shallow GCN and TCN blocks are constrained by small receptive fields and a lack of cross-dimension interaction capture. To tackle this limitation, we propose a lightweight module called the Dual Attention Module (DAM) for capturing cross-dimension interaction relationships in spatio-temporal skeletal data. It employs the frame attention mechanism to identify the most significant frames and the skeleton attention mechanism to capture broader relationships across fixed partitions with minimal parameters and flops. Furthermore, the proposed Dual Attention Normalizing Flow (DA-Flow) integrates the DAM as a post-processing unit after GCN within the normalizing flow framework. Simulations show that the proposed model is robust against noise and negative samples. Experimental results show that DA-Flow reaches competitive or better performance than the existing state-of-the-art (SOTA) methods in terms of the micro AUC metric with the fewest number of parameters. Moreover, we found that even without training, simply using random projection without dimensionality reduction on skeleton data enables substantial anomaly detection capabilities.

Jian Yue, Yanbo Gao, Shuai Li et al.

In-loop filtering is used in video coding to process the reconstructed frame in order to remove blocking artifacts. With the development of convolutional neural networks (CNNs), CNNs have been explored for in-loop filtering considering it can be treated as an image de-noising task. However, in addition to being a distorted image, the reconstructed frame is also obtained by a fixed line of block based encoding operations in video coding. It carries coding-unit based coding distortion of some similar characteristics. Therefore, in this paper, we address the filtering problem from two aspects, global appearance restoration for disrupted texture and local coding distortion restoration caused by fixed pipeline of coding. Accordingly, a three-stream global appearance and local coding distortion based fusion network is developed with a high-level global feature stream, a high-level local feature stream and a low-level local feature stream. Ablation study is conducted to validate the necessity of different features, demonstrating that the global features and local features can complement each other in filtering and achieve better performance when combined. To the best of our knowledge, we are the first one that clearly characterizes the video filtering process from the above global appearance and local coding distortion restoration aspects with experimental verification, providing a clear pathway to developing filter techniques. Experimental results demonstrate that the proposed method significantly outperforms the existing single-frame based methods and achieves 13.5%, 11.3%, 11.7% BD-Rate saving on average for AI, LDP and RA configurations, respectively, compared with the HEVC reference software.

Maurice Quach, Giuseppe Valenzise, Frederic Dufaux

Existing techniques to compress point cloud attributes leverage either geometric or video-based compression tools. We explore a radically different approach inspired by recent advances in point cloud representation learning. Point clouds can be interpreted as 2D manifolds in 3D space. Specifically, we fold a 2D grid onto a point cloud and we map attributes from the point cloud onto the folded 2D grid using a novel optimized mapping method. This mapping results in an image, which opens a way to apply existing image processing techniques on point cloud attributes. However, as this mapping process is lossy in nature, we propose several strategies to refine it so that attributes can be mapped to the 2D grid with minimal distortion. Moreover, this approach can be flexibly applied to point cloud patches in order to better adapt to local geometric complexity. In this work, we consider point cloud attribute compression; thus, we compress this image with a conventional 2D image codec. Our preliminary results show that the proposed folding-based coding scheme can already reach performance similar to the latest MPEG Geometry-based PCC (G-PCC) codec.

Florent Chiaroni, Ghazaleh Khodabandelou, Mohamed-Cherif Rahal et al.

With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversarial Networks (GANs) are not hampered by deterministic bias or need for specific dimensionality. However, existing GAN-based PU approaches also present some drawbacks such as sensitive dependence to prior knowledge, a cumbersome architecture or first-stage overfitting. To settle these issues, we propose to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to request the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. This enables the proposed model, referred to as D-GAN, to exclusively learn the counter-examples distribution without prior knowledge. Experiments demonstrate that our approach outperforms state-of-the-art PU methods without prior by overcoming their issues.

Florent Chiaroni, Mohamed-Cherif Rahal, Nicolas Hueber et al.

Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled training data. In the context of autonomous vehicles perception, this requirement is critical, as the distribution of sensor data can continuously change and include several unexpected variations. It turns out that a category of learning techniques, referred to as self-supervised learning (SSL), consists of replacing the manual labeling effort by an automatic labeling process. Thanks to their ability to learn on the application time and in varying environments, state-of-the-art SSL techniques provide a valid alternative to supervised learning for a variety of different tasks, including long-range traversable area segmentation, moving obstacle instance segmentation, long-term moving obstacle tracking, or depth map prediction. In this tutorial-style article, we present an overview and a general formalization of the concept of self-supervised learning (SSL) for autonomous vehicles perception. This formalization provides helpful guidelines for developing novel frameworks based on generic SSL principles. Moreover, it enables to point out significant challenges in the design of future SSL systems.

Aakanksha Rana, Praveer Singh, Giuseppe Valenzise et al.

A computationally fast tone mapping operator (TMO) that can quickly adapt to a wide spectrum of high dynamic range (HDR) content is quintessential for visualization on varied low dynamic range (LDR) output devices such as movie screens or standard displays. Existing TMOs can successfully tone-map only a limited number of HDR content and require an extensive parameter tuning to yield the best subjective-quality tone-mapped output. In this paper, we address this problem by proposing a fast, parameter-free and scene-adaptable deep tone mapping operator (DeepTMO) that yields a high-resolution and high-subjective quality tone mapped output. Based on conditional generative adversarial network (cGAN), DeepTMO not only learns to adapt to vast scenic-content (e.g., outdoor, indoor, human, structures, etc.) but also tackles the HDR related scene-specific challenges such as contrast and brightness, while preserving the fine-grained details. We explore 4 possible combinations of Generator-Discriminator architectural designs to specifically address some prominent issues in HDR related deep-learning frameworks like blurring, tiling patterns and saturation artifacts. By exploring different influences of scales, loss-functions and normalization layers under a cGAN setting, we conclude with adopting a multi-scale model for our task. To further leverage on the large-scale availability of unlabeled HDR data, we train our network by generating targets using an objective HDR quality metric, namely Tone Mapping Image Quality Index (TMQI). We demonstrate results both quantitatively and qualitatively, and showcase that our DeepTMO generates high-resolution, high-quality output images over a large spectrum of real-world scenes. Finally, we evaluate the perceived quality of our results by conducting a pair-wise subjective study which confirms the versatility of our method.

Navaneeth Kamballur Kottayil, Giuseppe Valenzise, Frederic Dufaux et al.

Accurate prediction of local distortion visibility thresholds is critical in many image and video processing applications. Existing methods require an accurate modeling of the human visual system, and are derived through pshycophysical experiments with simple, artificial stimuli. These approaches, however, are difficult to generalize to natural images with complex types of distortion. In this paper, we explore a different perspective, and we investigate whether it is possible to learn local distortion visibility from image quality scores. We propose a convolutional neural network based optimization framework to infer local detection thresholds in a distorted image. Our model is trained on multiple quality datasets, and the results are correlated with empirical visibility thresholds collected on complex stimuli in a recent study. Our results are comparable to state-of-the-art mathematical models that were trained on phsycovisual data directly. This suggests that it is possible to predict psychophysical phenomena from visibility information embedded in image quality scores.

Navaneeth K. Kottayil, Irene Cheng, Frederic Dufaux et al.

Image Quality Assessment (IQA) algorithms evaluate the perceptual quality of an image using evaluation scores that assess the similarity or difference between two images. We propose a new low-level feature based IQA technique, which applies filter-bank decomposition and center-surround methodology. Differing from existing methods, our model incorporates color intensity adaptation and frequency scaling optimization at each filter-bank level and spatial orientation to extract and enhance perceptually significant features. Our computational model exploits the concept of object detection and encapsulates characteristics proposed in other IQA algorithms in a unified architecture. We also propose a systematic approach to review the evolution of IQA algorithms using unbiased test datasets, instead of looking at individual scores in isolation. Experimental results demonstrate the feasibility of our approach.

Mohsen Abdoli, Félix Henry, Patric Brault et al.

A few years after standardization of the High Efficiency Video Coding (HEVC), now the Joint Video Exploration Team (JVET) group is exploring post-HEVC video compression technologies. In the intra prediction domain, this effort has resulted in an algorithm with 67 internal modes, new filters and tools which significantly improve HEVC. However, the improved algorithm still suffers from the long distance prediction inaccuracy problem. In this paper, we propose an In-Loop Residual coding Intra Prediction (ILR-IP) algorithm which utilizes inner-block reconstructed pixels as references to reduce the distance from predicted pixels. This is done by using the ILR signal for partially reconstructing each pixel, right after its prediction and before its block-level out-loop residual calculation. The ILR signal is decided in the rate-distortion sense, by a brute-force search on a QP-dependent finite codebook that is known to the decoder. Experiments show that the proposed ILR-IP algorithm improves the existing method in the Joint Exploration Model (JEM) up to 0.45% in terms of bit rate saving, without complexity overhead at the decoder side.