Related papers: COM3D: Leveraging Cross-View Correspondence and Cr…

Vision-language fine-tuning has emerged as an efficient paradigm for constructing multimodal foundation models. While textual context often highlights semantic relationships within an image, existing fine-tuning methods typically overlook…

The emergence of cross-modal foundation models has introduced numerous approaches grounded in text-image retrieval. However, on some domain-specific retrieval tasks, these models fail to focus on the key attributes required. To address this…

The majority of point cloud registration methods currently rely on extracting features from points. However, these methods are limited by their dependence on information obtained from a single modality of points, which can result in…

Image retrieval with hybrid-modality queries, also known as composing text and image for image retrieval (CTI-IR), is a retrieval task where the search intention is expressed in a more complex query format, involving both vision and text…

Composed Image Retrieval (CIR) retrieves target images using a multi-modal query that combines a reference image with text describing desired modifications. The primary challenge is effectively fusing this visual and textual information.…

Aiming at inferring 3D shapes from 2D images, 3D shape reconstruction has drawn huge attention from researchers in computer vision and deep learning communities. However, it is not practical to assume that 2D input images and their…

Existing methodologies in open vocabulary 3D semantic segmentation primarily concentrate on establishing a unified feature space encompassing 3D, 2D, and textual modalities. Nevertheless, traditional techniques such as global feature…

In recent years, cross-modal domain adaptation has been studied on the paired 2D image and 3D LiDAR data to ease the labeling costs for 3D LiDAR semantic segmentation (3DLSS) in the target domain. However, in such a setting the paired 2D…

We introduce MM-Mixing, a multi-modal mixing alignment framework for 3D understanding. MM-Mixing applies mixing-based methods to multi-modal data, preserving and optimizing cross-modal connections while enhancing diversity and improving…

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…

LiDAR-based place recognition serves as a crucial enabler for long-term autonomy in robotics and autonomous driving systems. Yet, prevailing methodologies relying on handcrafted feature extraction face dual challenges: (1) Inconsistent…

Cross-Modal Retrieval (CMR), which retrieves relevant items from one modality (e.g., audio) given a query in another modality (e.g., visual), has undergone significant advancements in recent years. This capability is crucial for robots to…

In recent years, 3D models have been utilized in many applications, such as auto-driver, 3D reconstruction, VR, and AR. However, the scarcity of 3D model data does not meet its practical demands. Thus, generating high-quality 3D models…

Transferring the style from one image onto another is a popular and widely studied task in computer vision. Yet, style transfer in the 3D setting remains a largely unexplored problem. To our knowledge, we propose the first learning-based…

To address 3D object retrieval, substantial efforts have been made to generate highly discriminative descriptors of 3D objects represented by a single modality, e.g., voxels, point clouds or multi-view images. It is promising to leverage…

Contrastive Language-Image Pre-training, benefiting from large-scale unlabeled text-image pairs, has demonstrated great performance in open-world vision understanding tasks. However, due to the limited Text-3D data pairs, adapting the…

Existing 3D foundation models typically align point clouds to frozen vision-language spaces like CLIP, which achieve strong cross-modal retrieval by compressing 3D shape into a global vector. However, this global-only alignment cannot…

The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks,…

Three-dimensional Morphable Models (3DMMs) are powerful statistical tools for representing the 3D surfaces of an object class. In this context, we identify an interesting question that has previously not received research attention: is it…

3D contrastive representation learning has exhibited remarkable efficacy across various downstream tasks. However, existing contrastive learning paradigms based on cosine similarity fail to deeply explore the potential intra-modal…