Related papers: Multiple Consistent 2D-3D Mappings for Robust Zero…

Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing imagery according to natural language expressions. Previous methods typically rely on sentence-level vision-language alignment, which struggles to exploit…

Open-vocabulary 3D object detection aims to localize and recognize objects beyond a fixed training taxonomy. In multi-view RGB settings, recent approaches often decouple geometry-based instance construction from semantic labeling,…

3D visual grounding (3DVG) is challenging due to the need to understand 3D spatial relations. While supervised approaches have achieved superior performance, they are constrained by the scarcity and high annotation costs of 3D…

A fundamental problem in the texturing of 3D meshes using pre-trained text-to-image models is to ensure multi-view consistency. State-of-the-art approaches typically use diffusion models to aggregate multi-view inputs, where common issues…

3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds. However, when we apply 3DGS to surface reconstruction tasks, especially in environments…

Spatial reasoning is a fundamental capability of multimodal large language models (MLLMs), yet their performance in open aerial environments remains underexplored. In this work, we present Open3D-VQA, a novel benchmark for evaluating MLLMs'…

Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relationship in 3D space over time, largely due to the scarcity of…

The 3D weakly-supervised visual grounding task aims to localize oriented 3D boxes in point clouds based on natural language descriptions without requiring annotations to guide model learning. This setting presents two primary challenges:…

We present a novel task for cross-dataset visual grounding in 3D scenes (Cross3DVG), which overcomes limitations of existing 3D visual grounding models, specifically their restricted 3D resources and consequent tendencies of overfitting a…

Medical Visual Grounding (MVG) aims to identify diagnostically relevant phrases from free-text radiology reports and localize their corresponding regions in medical images, providing interpretable visual evidence to support clinical…

Though recent advances in vision-language models (VLMs) have achieved remarkable progress across a wide range of multimodal tasks, understanding 3D spatial relationships from limited views remains a significant challenge. Previous reasoning…

Recent advances in Multi-modal Large Language Models (MLLMs) have showcased remarkable capabilities in vision-language understanding. However, enabling robust video spatial reasoning-the ability to comprehend object locations, orientations,…

We present a learning based approach for multi-view stereopsis (MVS). While current deep MVS methods achieve impressive results, they crucially rely on ground-truth 3D training data, and acquisition of such precise 3D geometry for…

Text-to-3D generation approaches have advanced significantly by leveraging pretrained 2D diffusion priors, producing high-quality and 3D-consistent outputs. However, they often fail to produce out-of-domain (OOD) or rare concepts, yielding…

Feed-forward reconstruction has been progressed rapidly, with the Visual Geometry Grounded Transformer (VGGT) being a notable baseline. However, directly applying VGGT to autonomous driving (AD) fails to capture three domain-specific…

Multi-view 3D object detection is a fundamental task in autonomous driving perception, where achieving a balance between detection accuracy and computational efficiency remains crucial. Sparse query-based 3D detectors efficiently aggregate…

Current Visual-Language Navigation (VLN) methodologies face a trade-off between semantic understanding and control precision. While Multimodal Large Language Models (MLLMs) offer superior reasoning, deploying them as low-level controllers…

In this work, we propose a novel approach to prioritize the depth map computation of multi-view stereo (MVS) to obtain compact 3D point clouds of high quality and completeness at low computational cost. Our prioritization approach operates…

Self-supervised Multi-view stereo (MVS) with a pretext task of image reconstruction has achieved significant progress recently. However, previous methods are built upon intuitions, lacking comprehensive explanations about the effectiveness…

Effective embodied exploration requires agents to accumulate and retain spatial knowledge over time. However, existing scene representations, such as discrete scene graphs or static view-based snapshots, lack \textit{post-hoc…