Related papers: PointAlign: Feature-Level Alignment Regularization…

This paper addresses the challenge of fine-grained alignment in Vision-and-Language Navigation (VLN) tasks, where robots navigate realistic 3D environments based on natural language instructions. Current approaches use contrastive learning…

Point cloud filtering, the main bottleneck of which is removing noise (outliers) while preserving geometric features, is a fundamental problem in 3D field. The two-step schemes involving normal estimation and position update have been shown…

The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data. Existing attempts usually face the problem of coarse alignment, e.g., the vision encoder struggles in localizing an…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and textual representations is not fully…

Vision language models (VLMs) have seen growing adoption in recent years, but many still struggle with basic spatial reasoning errors. We hypothesize that this is due to VLMs adopting pre-trained vision backbones, specifically vision…

Data augmentation is an effective regularization strategy for mitigating overfitting in deep neural networks, and it plays a crucial role in 3D vision tasks, where the point cloud data is relatively limited. While mixing-based augmentation…

Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…

The explosion of visual content available online underscores the requirement for an accurate machine assessor to robustly evaluate scores across diverse types of visual contents. While recent studies have demonstrated the exceptional…

Recent progress of semantic point clouds analysis is largely driven by synthetic data (e.g., the ModelNet and the ShapeNet), which are typically complete, well-aligned and noisy free. Therefore, representations of those ideal synthetic…

Recent advancements in vision-language pre-training (e.g. CLIP) have shown that vision models can benefit from language supervision. While many models using language modality have achieved great success on 2D vision tasks, the joint…

This paper presents a novel pipeline for 2D keypoint estima- tion of surgical tools by leveraging Vision Language Models (VLMs) fine- tuned using a low rank adjusting (LoRA) technique. Unlike traditional Convolutional Neural Network (CNN)…

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…

3D Visual Grounding (3DVG) focuses on locating objects in 3D scenes based on natural language descriptions, serving as a fundamental task for embodied AI and robotics. Recent advances in Multi-modal Large Language Models (MLLMs) have…

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…

Pretrained vision language models (VLMs) present an opportunity to caption unlabeled 3D objects at scale. The leading approach to summarize VLM descriptions from different views of an object (Luo et al., 2023) relies on a language model…

Category-level articulated object pose estimation focuses on the pose estimation of unknown articulated objects within known categories. Despite its significance, this task remains challenging due to the varying shapes and poses of objects,…

Achieving better alignment between vision embeddings and Large Language Models (LLMs) is crucial for enhancing the abilities of Multimodal LLMs (MLLMs), particularly for recent models that rely on powerful pretrained vision encoders and…

We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space between 3D and multi-modalities, enabling many promising…

Point cloud registration, a fundamental task in 3D vision, has achieved remarkable success with learning-based methods in outdoor environments. Unsupervised outdoor point cloud registration methods have recently emerged to circumvent the…

LiDAR-based 3D detection has made great progress in recent years. However, the performance of 3D detectors is considerably limited when deployed in unseen environments, owing to the severe domain gap problem. Existing domain adaptive 3D…