Related papers: Beyond First Impressions: Integrating Joint Multi-…

We present a deployment friendly, fast bottom-up framework for multi-person 3D human pose estimation. We adopt a novel neural representation of multi-person 3D pose which unifies the position of person instances with their corresponding 3D…

Multi-modal image fusion (MMIF) maps useful information from various modalities into the same representation space, thereby producing an informative fused image. However, the existing fusion algorithms tend to symmetrically fuse the…

Understanding 3D medical image volumes is a critical task in the medical domain. However, existing 3D convolution and transformer-based methods have limited semantic understanding of an image volume and also need a large set of volumes for…

Humans learn abstract concepts through multisensory synergy, and once formed, such representations can often be recalled from a single modality. Inspired by this principle, we introduce Concerto, a minimalist simulation of human concept…

Multimodal fusion leverages information across modalities to learn better feature representations with the goal of improving performance in fusion-based tasks. However, multimodal datasets, especially in medical settings, are typically…

Recent open-world 3D representation learning methods using Vision-Language Models (VLMs) to align 3D point cloud with image-text information have shown superior 3D zero-shot performance. However, CAD-rendered images for this alignment often…

Aligning signals from different modalities is an important step in vision-language representation learning as it affects the performance of later stages such as cross-modality fusion. Since image and text typically reside in different…

Multimodal object detection has attracted significant attention in both academia and industry for its enhanced robustness. Although numerous studies have focused on improving modality fusion strategies, most neglect fusion degradation, and…

Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various feature aggregation methods to transform deep features into…

Open-world 3D scene understanding is a critical challenge that involves recognizing and distinguishing diverse objects and categories from 3D data, such as point clouds, without relying on manual annotations. Traditional methods struggle…

Recent advances in Large Multimodal Models (LMM) have made it possible for various applications in human-machine interactions. However, developing LMMs that can comprehend, reason, and plan in complex and diverse 3D environments remains a…

In this paper, we aim to recover the 3D human pose from 2D body joints of a single image. The major challenge in this task is the depth ambiguity since different 3D poses may produce similar 2D poses. Although many recent advances in this…

Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipeline which transfers knowledge from seen classes with labels…

A major endeavor of computer vision is to represent, understand and extract structure from 3D data. Towards this goal, unsupervised learning is a powerful and necessary tool. Most current unsupervised methods for 3D shape analysis use…

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…

This paper presents a compact and accurate representation of 3D scenes that are observed by a LiDAR sensor and a monocular camera. The proposed method is based on the well-established Stixel model originally developed for stereo vision…

Multi-modal 3D object understanding has gained significant attention, yet current approaches often assume complete data availability and rigid alignment across all modalities. We present CrossOver, a novel framework for cross-modal 3D scene…

Multi-modal medical imaging enables comprehensive diagnostics, yet current foundation models process 2D (e.g. X-ray) and 3D (e.g. CT) data with separate, dimensionality-specific architectures. We present MultiMedVision, a unified framework…

The development of 3D Vision-Language Models (VLMs), crucial for applications in robotics, autonomous driving, and augmented reality, is severely constrained by the scarcity of paired 3D-text data. Existing methods rely solely on next-token…

Recent advances in scene understanding have leveraged multimodal large language models (MLLMs) for 3D reasoning by capitalizing on their strong 2D pretraining. However, the lack of explicit 3D data during MLLM pretraining limits 3D…