Related papers: Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Inc…

We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds. We adopt the commonly used multi-modal contrastive learning framework for representation alignment, but with a specific focus…

The limited scale of current 3D shape datasets hinders the advancements in 3D shape understanding, and motivates multi-modal learning approaches which transfer learned knowledge from data-abundant 2D image and language modalities to 3D…

Generalised 3D Referring Expression Segmentation (3D-GRES) localizes objects in 3D scenes based on natural language, even when descriptions match multiple or zero targets. Existing methods rely solely on sparse point clouds, lacking rich…

Due to the significant effort required for data collection and annotation in 3D perception tasks, mixed sample data augmentation (MSDA) has been widely studied to generate diverse training samples by mixing existing data. Recently, many…

3D object detection serves as the core basis of the perception tasks in autonomous driving. Recent years have seen the rapid progress of multi-modal fusion strategies for more robust and accurate 3D object detection. However, current…

Image-to-point cloud registration methods typically follow a coarse-to-fine pipeline, extracting patch-level correspondences and refining them into dense pixel-to-point matches. However, in scenes with repetitive patterns, images often lack…

Multimodal learning plays a critical role in e-commerce recommendation platforms today, enabling accurate recommendations and product understanding. However, existing vision-language models, such as CLIP, face key challenges in e-commerce…

3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation.…

Few-shot Generalist Anomaly Detection requires models to generalize to novel categories without retraining, posing significant challenges in real-world scenarios with scarce samples and rapidly changing categories. Existing CLIP-based…

3D content inherently encompasses multi-modal characteristics and can be projected into different modalities (e.g., RGB images, RGBD, and point clouds). Each modality exhibits distinct advantages in 3D asset modeling: RGB images contain…

In this paper, we explore the capabilities of multimodal inputs to 3D Gaussian Splatting (3DGS) based Radiance Field Rendering. We present LiDAR-3DGS, a novel method of reinforcing 3DGS inputs with LiDAR generated point clouds to…

Establishing dense correspondence across 3D shapes is crucial for fundamental downstream tasks, including texture transfer, shape interpolation, and robotic manipulation. However, learning these mappings without manual supervision remains a…

Reconstructing 3D shapes from a single image plays an important role in computer vision. Many methods have been proposed and achieve impressive performance. However, existing methods mainly focus on extracting semantic information from…

Industrial anomaly detection based on RGB-3D multimodal data has emerged as a mainstream paradigm for intelligent quality inspection. However, existing unsupervised methods suffer from two critical limitations: ambiguous cross-modal…

Recent advancements in deep generative models, particularly with the application of CLIP (Contrastive Language Image Pretraining) to Denoising Diffusion Probabilistic Models (DDPMs), have demonstrated remarkable effectiveness in text to…

Advancements in cross-modal feature extraction and integration have significantly enhanced performance in few-shot learning tasks. However, current multi-modal object detection (MM-OD) methods often experience notable performance…

In this paper, we investigate the problem of weakly supervised 3D vehicle detection. Conventional methods for 3D object detection need vast amounts of manually labelled 3D data as supervision signals. However, annotating large datasets…

Recent advances in multi-modal pre-training methods have shown promising effectiveness in learning 3D representations by aligning multi-modal features between 3D shapes and their corresponding 2D counterparts. However, existing multi-modal…

Class incremental learning consists in training discriminative models to classify an increasing number of classes over time. However, doing so using only the newly added class data leads to the known problem of catastrophic forgetting of…

Our research focuses on few-shot fine-grained image classification, which faces two major challenges: appearance similarity of fine-grained objects and limited number of samples. To preserve the appearance details of images, traditional…