Achieving 3D hand-object pose estimation in interaction scenarios is challenging due to the severe occlusion generated during the interaction. Existing methods address this issue by utilizing the correlation between the hand and object poses as additional cues. They usually first extract the hand and object features from their respective regions and then refine them with each other. However, this paradigm disregards the role of a broad range of image context. To address this problem, we propose a novel and robust approach that learns a broad range of context by imposing priors. First, we build this approach using stacked transformer decoder layers. These layers are required for extracting image-wide context and regional hand or object features by constraining cross-attention operations. We share the context decoder layer parameters between the hand and object pose estimations to avoid interference in the context-learning process. This imposes a prior, indicating that the hand and object are mutually the most important context for each other, significantly enhancing the robustness of obtained context features. Second, since they play different roles, we provide customized feature maps for the context, hand, and object decoder layers. This strategy facilitates the disentanglement of these layers, reducing the feature learning complexity. Finally, we conduct extensive experiments on the popular HO3D and Dex-YCB databases. The experimental results indicate that our method significantly outperforms state-of-the-art approaches and can be applied to other hand pose estimation tasks. Code is available at https://github.com/zskuang58/LCP.

Joint hand and object pose estimation from a single image is extremely challenging as serious occlusion often occurs when the hand and object interact. Existing approaches typically first extract coarse hand and object features from a single backbone, then further enhance them with reference to each other via interaction modules. However, these works usually ignore that the hand and object are competitive in feature learning, since the backbone takes both of them as foreground and they are usually mutually occluded. In this paper, we propose a novel Harmonious Feature Learning Network (HFL-Net). HFL-Net introduces a new framework that combines the advantages of single-and double-stream backbones: it shares the parameters of the low-and high-level convolutional layers of a common ResNet-50 model for the hand and object, leaving the middle-level layers unshared. This strategy enables the hand and the object to be extracted as the sole targets by the middle-level layers, avoiding their competition in feature learning. The shared high-level layers also force their features to be harmonious, thereby facilitating their mutual feature enhancement. In particular, we propose to enhance the feature of the hand via concatenation with the feature in the same location from the object stream. A subsequent self-attention layer is adopted to deeply fuse the concatenated feature. Experimental results show that our proposed approach consistently outperforms state-of-the-art methods on the popular HO3D and Dex-Ycb databases. Notably, the performance of our model on hand pose estimation even surpasses that of existing works that only perform the single-hand pose estimation task. Code is available at https://github.com/lzjJf12/HFL-Net.

Most reference-based image super-resolution (RefSR) methods directly leverage the raw features extracted from a pretrained VGG encoder to transfer the matched texture information from a reference image to a low-resolution image. We argue that simply operating on these raw features neglects the influence of irrelevant and redundant information and the importance of abundant high-frequency representations, leading to undesirable texture matching and transfer results. Taking the advantages of wavelet transformation, which represents the contextual and textural information of features at different scales, we propose a Wavelet-based Texture Reformation Network (WTRN) for RefSR. We first decompose the extracted texture features into low-frequency and high-frequency sub-bands and conduct feature matching on the low-frequency component. Based on the correlation map obtained from the feature matching process, we then separately swap and transfer wavelet-domain features at different stages of the network. Furthermore, a wavelet-based texture adversarial loss is proposed to make the network generate more visually plausible textures. Experiments on four benchmark datasets demonstrate that our proposed method outperforms previous RefSR methods both quantitatively and qualitatively. The source code is available at https://github.com/zskuang58/WTRN-TIP.

Bounding box regression is a very effective method to improve the localization accuracy of object detection. Recently, the IoU-based regression losses have been widely used in object detection algorithms. However, we observe that they degenerate seriously in the late training period, leading to slow convergence and inaccurate localization. In this paper, we design a Fast Intersection over Union (FIoU) loss, which can not only keep the advantages but also solve the weakness of IoU-based losses. Furthermore, FIoU can be directly applied to Non-Maximum Suppression (NMS) as a criterion to improve the localization performance. Numerous experiments on two popular benchmark datasets show that our method is superior to other the-state-of-art methods.