S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal

In this paper we present S3R-Net, the Self-Supervised Shadow Removal Network. The two-branch WGAN model achieves self-supervision relying on the unify-and-adaptphenomenon - it unifies the style of the output data and infers its characteristics from a database of unaligned shadow-free reference images. This approach stands in contrast to the large body of supervised frameworks. S3R-Net also differentiates itself from the few existing self-supervised models operating in a cycle-consistent manner, as it is a non-cyclic, unidirectional solution. The proposed framework achieves comparable numerical scores to recent selfsupervised shadow removal models while exhibiting superior qualitative performance and keeping the computational cost low.

ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet

This paper introduces ViscoNet, a novel method that enhances text-to-image human generation models with visual prompting. Unlike existing methods that rely on lengthy text descriptions to control the image structure, ViscoNet allows users to specify the visual appearance of the target object with a reference image. ViscoNet disentangles the object's appearance from the image background and injects it into a pre-trained latent diffusion model (LDM) model via a ControlNet branch. This way, ViscoNet mitigates the style mode collapse problem and enables precise and flexible visual control. We demonstrate the effectiveness of ViscoNet on human image generation, where it can manipulate visual attributes and artistic styles with text and image prompts. We also show that ViscoNet can learn visual conditioning from small and specific object domains while preserving the generative power of the LDM backbone.

CAD -- Contextual Multi-modal Alignment for Dynamic AVQA

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.

PAT: Position-Aware Transformer for Dense Multi-Label Action Detection

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.

UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer

Existing person image generative models can do either image generation or pose transfer but not both. We propose a unified diffusion model, UPGPT to provide a universal solution to perform all the person image tasks - generative, pose transfer, and editing. With fine-grained multimodality and disentanglement capabilities, our approach offers fine-grained control over the generation and the editing process of images using a combination of pose, text, and image, all without needing a semantic segmentation mask which can be challenging to obtain or edit. We also pioneer the parameterized body SMPL model in pose-guided person image generation to demonstrate new capability - simultaneous pose and camera view interpolation while maintaining a person's appearance. Results on the benchmark DeepFashion dataset show that UPGPT is the new state-of-the-art while simultaneously pioneering new capabilities of edit and pose transfer in human image generation.

SEM-POS: Grammatically and Semantically Correct Video Captioning

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.

Pose Guided Multi-person Image Generation From Text

Transformers have recently been shown to generate high quality images from texts. However, existing methods struggle to create high fidelity full-body images, especially multiple people. A person's pose has a high degree of freedom that is difficult to describe using words only; this creates errors in the generated image, such as incorrect body proportions and pose. We propose a pose-guided text-to-image model, using pose as an additional input constraint. Using the proposed Keypoint Pose Encoding (KPE) to encode human pose into low dimensional representation, our model can generate novel multi-person images accurately representing the pose and text descriptions provided, with minimal errors. We demonstrate that KPE is invariant to changes in the target image domain and image resolution; we show results on the Deepfashion dataset and create a new multi-person Deepfashion dataset to demonstrate the multi-capabilities of our approach.

SILT: Self-supervised Lighting Transfer Using Implicit Image Decomposition

We present SILT, a Self-supervised Implicit Lighting Transfer method. Unlike previous research on scene relighting, we do not seek to apply arbitrary new lighting configurations to a given scene. Instead, we wish to transfer the lighting style from a database of other scenes, to provide a uniform lighting style regardless of the input. The solution operates as a two-branch network that first aims to map input images of any arbitrary lighting style to a unified domain, with extra guidance achieved through implicit image decomposition. We then remap this unified input domain using a discriminator that is presented with the generated outputs and the style reference, i.e. images of the desired illumination conditions. Our method is shown to outperform supervised relighting solutions across two different datasets without requiring lighting supervision.

Multi-person Implicit Reconstruction from a Single Image

We present a new end-to-end learning framework to obtain detailed and spatially coherent reconstructions of multiple people from a single image. Existing multi-person methods suffer from two main drawbacks: they are often model-based and therefore cannot capture accurate 3D models of people with loose clothing and hair; or they require manual intervention to resolve occlusions or interactions. Our method addresses both limitations by introducing the first end-to-end learning approach to perform model-free implicit reconstruction for realistic 3D capture of multiple clothed people in arbitrary poses (with occlusions) from a single image. Our network simultaneously estimates the 3D geometry of each person and their 6DOF spatial locations, to obtain a coherent multi-human reconstruction. In addition, we introduce a new synthetic dataset that depicts images with a varying number of inter-occluded humans and a variety of clothing and hair styles. We demonstrate robust, high-resolution reconstructions on images of multiple humans with complex occlusions, loose clothing and a large variety of poses and scenes. Our quantitative evaluation on both synthetic and real-world datasets demonstrates state-of-the-art performance with significant improvements in the accuracy and completeness of the reconstructions over competing approaches.

Temporal Consistency Loss for High Resolution Textured and Clothed 3DHuman Reconstruction from Monocular Video

We present a novel method to learn temporally consistent 3D reconstruction of clothed people from a monocular video. Recent methods for 3D human reconstruction from monocular video using volumetric, implicit or parametric human shape models, produce per frame reconstructions giving temporally inconsistent output and limited performance when applied to video. In this paper, we introduce an approach to learn temporally consistent features for textured reconstruction of clothed 3D human sequences from monocular video by proposing two advances: a novel temporal consistency loss function; and hybrid representation learning for implicit 3D reconstruction from 2D images and coarse 3D geometry. The proposed advances improve the temporal consistency and accuracy of both the 3D reconstruction and texture prediction from a monocular video. Comprehensive comparative performance evaluation on images of people demonstrates that the proposed method significantly outperforms the state-of-the-art learning-based single image 3D human shape estimation approaches achieving significant improvement of reconstruction accuracy, completeness, quality and temporal consistency.