Related papers: Direction-aware 3D Large Multimodal Models

Human face pose estimation aims at estimating the gazing direction or head postures with 2D images. It gives some very important information such as communicative gestures, saliency detection and so on, which attracts plenty of attention…

The rapid development of Large Multimodal Models (LMMs) for 2D images and videos has spurred efforts to adapt these models for interpreting 3D scenes. However, the absence of large-scale 3D vision-language datasets has posed a significant…

In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map. Compared to RGB…

The success of deep learning methods led to significant breakthroughs in 3-D point cloud processing tasks with applications in remote sensing. Existing methods utilize convolutions that have some limitations, as they assume a uniform input…

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

While Vision-Language Models (VLMs) show significant promise for end-to-end autonomous driving by leveraging the common sense embedded in language models, their reliance on 2D image cues for complex scene understanding and decision-making…

The rapidly developing field of large multimodal models (LMMs) has led to the emergence of diverse models with remarkable capabilities. However, existing benchmarks fail to comprehensively, objectively and accurately evaluate whether LMMs…

We address the problem of learning accurate 3D shape and camera pose from a collection of unlabeled category-specific images. We train a convolutional network to predict both the shape and the pose from a single image by minimizing the…

Unsupervised domain adaptation for LiDAR-based 3D object detection (3D UDA) based on the teacher-student architecture with pseudo labels has achieved notable improvements in recent years. Although it is quite popular to collect point clouds…

Cross-modal 3D retrieval is a critical yet challenging task, aiming to achieve bi-directional retrieval between 3D and text modalities. Current methods predominantly rely on a certain 3D representation (e.g., point cloud), with few…

Understanding human emotions from multimodal signals poses a significant challenge in affective computing and human-robot interaction. While multimodal large language models (MLLMs) have excelled in general vision-language tasks, their…

Sharing virtual content among multiple smart glasses wearers is an essential feature of a seamless Collaborative Augmented Reality experience. To enable the sharing, local coordinate systems of the underlying 6D ego-pose trackers, running…

Humans possess spatial reasoning abilities that enable them to understand spaces through multimodal observations, such as vision and sound. Large multimodal reasoning models extend these abilities by learning to perceive and reason, showing…

In the realm of point cloud registration, the most prevalent pose evaluation approaches are statistics-based, identifying the optimal transformation by maximizing the number of consistent correspondences. However, registration recall…

In this report, we present a cross-view multi-modal object segmentation approach for the object correspondence task in the Ego-Exo4D Correspondence Challenges 2025. Given object queries from one perspective (e.g., ego view), the goal is to…

We propose a novel zero-shot approach for keypoint detection on 3D shapes. Point-level reasoning on visual data is challenging as it requires precise localization capability, posing problems even for powerful models like DINO or CLIP.…

3D spatial reasoning is the ability to analyze and interpret the positions, orientations, and spatial relationships of objects within the 3D space. This allows models to develop a comprehensive understanding of the 3D scene, enabling their…

High-precision vehicle localization with commercial setups is a crucial technique for high-level autonomous driving tasks. Localization with a monocular camera in LiDAR map is a newly emerged approach that achieves promising balance between…

Depth estimation is usually ill-posed and ambiguous for monocular camera-based 3D multi-person pose estimation. Since LiDAR can capture accurate depth information in long-range scenes, it can benefit both the global localization of…

3D localization in Multimodal Large Language Models (MLLMs), including 3D object detection and 3D visual grounding, is fundamentally limited by camera intrinsic ambiguity: the same image admits different 3D scenes under different cameras.…