Related papers: Direction-aware 3D Large Multimodal Models

In this paper, we study a problem of egocentric scene understanding, i.e., predicting depths and surface normals from an egocentric image. Egocentric scene understanding poses unprecedented challenges: (1) due to large head movements, the…

Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains comparatively underexplored. Similar to language models,…

Automated pose correction remains a significant challenge in AI-driven fitness systems, despite extensive research in activity recognition. This work presents PosePilot, a novel system that integrates pose recognition with real-time…

In this paper, we propose a novel approach to enhance the 3D body pose estimation of a person computed from videos captured from a single wearable camera. The key idea is to leverage high-level features linking first- and third-views in a…

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in multimodal reasoning. However, they often excessively rely on textual information during the later stages of inference, neglecting the crucial integration of…

Monocular 3D human pose estimation remains a challenging and ill-posed problem, particularly in real-time settings and unconstrained environments. While direct imageto-3D approaches require large annotated datasets and heavy models,…

Self-supervised learning of depth and ego-motion from unlabeled monocular video has acquired promising results and drawn extensive attention. Most existing methods jointly train the depth and pose networks by photometric consistency of…

Modern Large Multimodal Models (LMMs) have demonstrated extraordinary ability in static image and single-state spatial-temporal understanding. However, their capacity to comprehend the dynamic changes of objects within a shared spatial…

Face alignment aims to estimate the locations of a set of landmarks for a given image. This problem has received much attention as evidenced by the recent advancement in both the methodology and performance. However, most of the existing…

In perception, multiple sensory information is integrated to map visual information from 2D views onto 3D objects, which is beneficial for understanding in 3D environments. But in terms of a single 2D view rendered from different angles,…

We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in interpretable representation learning, we exploit 3D geometry to fuse input images into…

Although multimodal large language models (MLLMs) have achieved promising results on a wide range of vision-language tasks, their ability to perceive and understand human faces is rarely explored. In this work, we comprehensively evaluate…

Large-scale vision 2D vision language models, such as CLIP can be aligned with a 3D encoder to learn generalizable (open-vocabulary) 3D vision models. However, current methods require supervised pre-training for such alignment, and the…

This paper introduces a novel self-supervised learning framework for enhancing 3D perception in autonomous driving scenes. Specifically, our approach, namely NCLR, focuses on 2D-3D neural calibration, a novel pretext task that estimates the…

We present a new self-supervised approach, SelfPose3d, for estimating 3d poses of multiple persons from multiple camera views. Unlike current state-of-the-art fully-supervised methods, our approach does not require any 2d or 3d ground-truth…

6D pose estimation refers to object recognition and estimation of 3D rotation and 3D translation. The key technology for estimating 6D pose is to estimate pose by extracting enough features to find pose in any environment. Previous methods…

Dense 3D reconstruction and ego-motion estimation are key challenges in autonomous driving and robotics. Compared to the complex, multi-modal systems deployed today, multi-camera systems provide a simpler, low-cost alternative. However,…

Pre-trained language models (PLM) have demonstrated their effectiveness for a broad range of information retrieval and natural language processing tasks. As the core part of PLM, multi-head self-attention is appealing for its ability to…

In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches to addressing this task have shown great success on synthetic datasets, we have observed them to fail in…

Egocentric Video Question Answering (QA) requires models to handle long-horizon temporal reasoning, first-person perspectives, and specialized challenges like frequent camera movement. This paper systematically evaluates both proprietary…