Fine-grained grocery object recognition is an important computer vision problem with broad applications in automatic checkout, in-store robotic navigation, and assistive technologies for the visually impaired. Existing datasets on groceries are mainly 2D images. Models trained on these datasets are limited to learning features from the regular 2D grids. While portable 3D sensors such as Kinect were commonly available for mobile phones, sensors such as LiDAR and TrueDepth, have recently been integrated into mobile phones. Despite the availability of mobile 3D sensors, there are currently no dedicated real-world large-scale benchmark 3D datasets for grocery. In addition, existing 3D datasets lack fine-grained grocery categories and have limited training samples. Furthermore, collecting data by going around the object versus the traditional photo capture makes data collection cumbersome. Thus, we introduce a large-scale grocery dataset called 3DGrocery100. It constitutes 100 classes, with a total of 87,898 3D point clouds created from 10,755 RGB-D single-view images. We benchmark our dataset on six recent stateof-the-art 3D point cloud classification models. Additionally, we also benchmark the dataset on few-shot and continual learning point cloud classification tasks. Project Page: https://bigdatavision.org/3DGrocery100/.

Due to their text-to-image synthesis feature, diffusion models have recently seen a rise in visual perception tasks, such as depth estimation. The lack of good-quality datasets makes the extraction of a fine-grain semantic context challenging for the diffusion models. The semantic context with fewer details further worsens the process of creating effective text embeddings that will be used as input for diffusion models. In this paper, we propose a novel EDADepth, an enhanced data augmentation method to estimate monocular depth without using additional training data. We use Swin2SR, a super-resolution model, to enhance the quality of input images. We employ the BEiT pretrained semantic segmentation model to better extract text embeddings. We use the BLIP-2 tokenizer to generate tokens from these text embeddings. The novelty of our approach is the introduction of Swin2SR, the BEiT model, and the BLIP-2 tokenizer in the diffusion-based pipeline for the monocular depth estimation. Our model achieves state-of-the-art results (SOTA) on the$\delta_{3}$metric on the NYUv2 and KITTI datasets. It also achieves results comparable to those of the SOTA models in the RMSE and REL metrics. Finally, we also show improvements in the visualization of the estimated depth compared to the SOTA diffusion-based monocular depth estimation models. Code: https://github.com/edadepthmde/EDADepth_ICMLA.

Unlike images, meshes are irregular and unstructured. Thus, it is not trivial to extend existing image-based deep learning approaches for mesh analysis. In this paper, inspired by dilated convolutions for images, we proffer dilated convolutions for meshes. Our Dilated Mesh Convolution (DMC) unit inflates the kernels’ receptive field without increasing the number of learnable parameters. We also propose a Stacked Dilated Mesh Convolution (SDMC) block by stacking DMC units. It considers spatial regions around mesh faces’ at multiple scales while summarizing the neighboring contextual information. We accommodated SDMC in MeshNet to classify 3D meshes. Experimental results demonstrate that this redesigned model significantly improves classification accuracy on multiple data sets. Code is available at https://github.com/VimsLab/DMC.

Polygon meshes are a popular representation in computer graphics. They efficiently provide delineations of complex 3D shapes. However, their irregular structure hinders mesh analysis efforts in deep learning frameworks; few neural networks exist to describe meshes. MeshNet is a pioneer in this direction. In this paper, we propose a novel neural network that is substantially deeper than its MeshNet predecessor. This increase in depth is achieved through our specialized convolution and pooling blocks that operate on mesh faces. Our network named MeshNet++ learns local structures at multiple scales and is also robust to shortcomings of mesh decimation. We evaluated it for the shape classification task on various data sets, and results significantly higher than state-of-the-art were observed. In particular, results demonstrated that even a small number of examples suffice for training MeshNet++. Our code is available at https://github.com/VimsLab/MeshNet2.