Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular approaches still struggle to recover fine geometric details such as face, hands or cloth wrinkles. They are also easily prone to depth ambiguities that result in distorted geometries along the camera optical axis. In this paper, we explore the benefits of incorporating depth observations in the reconstruction process by introducing ANIM, a novel method that reconstructs arbitrary 3D human shapes from single-view RGB-D images with an unprecedented level of accuracy. Our model learns geometric details from both multi-resolution pixel-aligned and voxel-aligned features to leverage depth information and enable spatial relationships, mitigating depth ambiguities. We further enhance the quality of the reconstructed shape by introducing a depth-supervision strategy, which improves the accuracy of the signed distance field estimation of points that lie on the reconstructed surface. Experiments demonstrate that ANIM outperforms state-of-the-art works that use RGB, surface normals, point cloud or RGB-D data as input. In addition, we introduce ANIM-Real, a new multi-modal dataset comprising high-quality scans paired with consumer-grade RGB-D camera, and our protocol to fine-tune ANIM, enabling high-quality reconstruction from real-world human capture.
In the context of Audio Visual Question Answering (AVQA) tasks, the audio visual modalities could be learnt on three levels: 1) Spatial, 2) Temporal, and 3) Semantic. Existing AVQA methods suffer from two major shortcomings; the audio-visual (AV) information passing through the network isn't aligned on Spatial and Temporal levels; and, inter-modal (audio and visual) Semantic information is often not balanced within a context; this results in poor performance. In this paper, we propose a novel end-to-end Contextual Multi-modal Alignment (CAD) network that addresses the challenges in AVQA methods by i) introducing a parameter-free stochastic Contextual block that ensures robust audio and visual alignment on the Spatial level; ii) proposing a pre-training technique for dynamic audio and visual alignment on Temporal level in a self-supervised setting, and iii) introducing a cross-attention mechanism to balance audio and visual information on Semantic level. The proposed novel CAD network improves the overall performance over the state-of-the-art methods on average by 9.4% on the MUSIC-AVQA dataset. We also demonstrate that our proposed contributions to AVQA can be added to the existing methods to improve their performance without additional complexity requirements.
We present PAT, a transformer-based network that learns complex temporal co-occurrence action dependencies in a video by exploiting multi-scale temporal features. In existing methods, the self-attention mechanism in transformers loses the temporal positional information, which is essential for robust action detection. To address this issue, we (i) embed relative positional encoding in the self-attention mechanism and (ii) exploit multi-scale temporal relationships by designing a novel non hierarchical network, in contrast to the recent transformer-based approaches that use a hierarchical structure. We argue that joining the self-attention mechanism with multiple sub-sampling processes in the hierarchical approaches results in increased loss of positional information. We evaluate the performance of our proposed approach on two challenging dense multi-label benchmark datasets, and show that PAT improves the current state-of-the-art result by 1.1% and 0.6% mAP on the Charades and MultiTHUMOS datasets, respectively, thereby achieving the new state-of-the-art mAP at 26.5% and 44.6%, respectively. We also perform extensive ablation studies to examine the impact of the different components of our proposed network.
Generating grammatically and semantically correct captions in video captioning is a challenging task. The captions generated from the existing methods are either word-by-word that do not align with grammatical structure or miss key information from the input videos. To address these issues, we introduce a novel global-local fusion network, with a Global-Local Fusion Block (GLFB) that encodes and fuses features from different parts of speech (POS) components with visual-spatial features. We use novel combinations of different POS components - 'determinant + subject', 'auxiliary verb', 'verb', and 'determinant + object' for supervision of the POS blocks - Det + Subject, Aux Verb, Verb, and Det + Object respectively. The novel global-local fusion network together with POS blocks helps align the visual features with language description to generate grammatically and semantically correct captions. Extensive qualitative and quantitative experiments on benchmark MSVD and MSRVTT datasets demonstrate that the proposed approach generates more grammatically and semantically correct captions compared to the existing methods, achieving the new state-of-the-art. Ablations on the POS blocks and the GLFB demonstrate the impact of the contributions on the proposed method.
We propose a novel framework to reconstruct super-resolution human shape from a single low-resolution input image. The approach overcomes limitations of existing approaches that reconstruct 3D human shape from a single image, which require high-resolution images together with auxiliary data such as surface normal or a parametric model to reconstruct high-detail shape. The proposed framework represents the reconstructed shape with a high-detail implicit function. Analogous to the objective of 2D image super-resolution, the approach learns the mapping from a low-resolution shape to its high-resolution counterpart and it is applied to reconstruct 3D shape detail from low-resolution images. The approach is trained end-to-end employing a novel loss function which estimates the information lost between a low and high-resolution representation of the same 3D surface shape. Evaluation for single image reconstruction of clothed people demonstrates that our method achieves high-detail surface reconstruction from low-resolution images without auxiliary data. Extensive experiments show that the proposed approach can estimate super-resolution human geometries with a significantly higher level of detail than that obtained with previous approaches when applied to low-resolution images.
Active speaker detection (ASD) is a multi-modal task that aims to identify who, if anyone, is speaking from a set of candidates. Current audio-visual approaches for ASD typically rely on visually pre-extracted face tracks (sequences of consecutive face crops) and the respective monaural audio. However, their recall rate is often low as only the visible faces are included in the set of candidates. Monaural audio may successfully detect the presence of speech activity but fails in localizing the speaker due to the lack of spatial cues. Our solution extends the audio front-end using a microphone array. We train an audio convolutional neural network (CNN) in combination with beamforming techniques to regress the speaker's horizontal position directly in the video frames. We propose to generate weak labels using a pre-trained active speaker detector on pre-extracted face tracks. Our pipeline embraces the "student-teacher" paradigm, where a trained "teacher" network is used to produce pseudo-labels visually. The "student" network is an audio network trained to generate the same results. At inference, the student network can independently localize the speaker in the visual frames directly from the audio input. Experimental results on newly collected data prove that our approach significantly outperforms a variety of other baselines as well as the teacher network itself. It results in an excellent speech activity detector too.
A common problem in the 4D reconstruction of people from multi-view video is the quality of the captured dynamic texture appearance which depends on both the camera resolution and capture volume. Typically the requirement to frame cameras to capture the volume of a dynamic performance ($>50m^3$) results in the person occupying only a small proportion $<$ 10% of the field of view. Even with ultra high-definition 4k video acquisition this results in sampling the person at less-than standard definition 0.5k video resolution resulting in low-quality rendering. In this paper we propose a solution to this problem through super-resolution appearance transfer from a static high-resolution appearance capture rig using digital stills cameras ($> 8k$) to capture the person in a small volume ($<8m^3$). A pipeline is proposed for super-resolution appearance transfer from high-resolution static capture to dynamic video performance capture to produce super-resolution dynamic textures. This addresses two key problems: colour mapping between different camera systems; and dynamic texture map super-resolution using a learnt model. Comparative evaluation demonstrates a significant qualitative and quantitative improvement in rendering the 4D performance capture with super-resolution dynamic texture appearance. The proposed approach reproduces the high-resolution detail of the static capture whilst maintaining the appearance dynamics of the captured video.
This paper proposes a novel Attention-based Multi-Reference Super-resolution network (AMRSR) that, given a low-resolution image, learns to adaptively transfer the most similar texture from multiple reference images to the super-resolution output whilst maintaining spatial coherence. The use of multiple reference images together with attention-based sampling is demonstrated to achieve significantly improved performance over state-of-the-art reference super-resolution approaches on multiple benchmark datasets. Reference super-resolution approaches have recently been proposed to overcome the ill-posed problem of image super-resolution by providing additional information from a high-resolution reference image. Multi-reference super-resolution extends this approach by providing a more diverse pool of image features to overcome the inherent information deficit whilst maintaining memory efficiency. A novel hierarchical attention-based sampling approach is introduced to learn the similarity between low-resolution image features and multiple reference images based on a perceptual loss. Ablation demonstrates the contribution of both multi-reference and hierarchical attention-based sampling to overall performance. Perceptual and quantitative ground-truth evaluation demonstrates significant improvement in performance even when the reference images deviate significantly from the target image. The project website can be found at https://marcopesavento.github.io/AMRSR/