相关论文: GroundFlow: A Plug-in Module for Temporal Reasonin…

Visual-spatial understanding, the ability to infer object relationships and layouts from visual input, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, existing methods face spatial…

Point cloud completion aims to recover complete 3D geometry from partial observations caused by limited viewpoints and occlusions. Existing learning-based works, including 3D Convolutional Neural Network (CNN)-based, point-based, and…

Point cloud semantic segmentation from projected views, such as range-view (RV) and bird's-eye-view (BEV), has been intensively investigated. Different views capture different information of point clouds and thus are complementary to each…

Prior studies on 3D scene understanding have primarily developed specialized models for specific tasks or required task-specific fine-tuning. In this study, we propose Grounded 3D-LLM, which explores the potential of 3D large multi-modal…

3D visual grounding (3DVG) aims to locate objects in a 3D scene with natural language descriptions. Supervised methods have achieved decent accuracy, but have a closed vocabulary and limited language understanding ability. Zero-shot methods…

Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision and language tasks. However, their ability to reason about spatial arrangements remains limited. In this work, we introduce Spatial Region GPT (SpatialRGPT)…

3D visual grounding involves finding a target object in a 3D scene that corresponds to a given sentence query. Although many approaches have been proposed and achieved impressive performance, they all require dense object-sentence pair…

Flow matching policies learn continuous velocity fields that transport noise to actions, enabling fast deterministic inference for robot manipulation. However, standard training optimizes a pointwise velocity objective while inference…

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…

Understanding 3D point clouds through language remains a fundamental challenge in computer graphics and visual computing, due to the irregular structure of point cloud data and the lack of explicit reasoning in existing 3D multimodal…

Learning without supervision how to predict 3D scene flows from point clouds is essential to many perception systems. We propose a novel learning framework for this task which improves the necessary regularization. Relying on the assumption…

3D affordance segmentation aims to link human instructions to touchable regions of 3D objects for embodied manipulations. Existing efforts typically adhere to single-object, single-affordance paradigms, where each affordance type or…

Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) based on the given expression text. This task simulates the common referential relationships…

Earthquake hazard analysis and design of spatially distributed infrastructure, such as power grids and energy pipeline networks, require scenario-specific ground-motion time histories with realistic frequency content and spatiotemporal…

Vision-Language-Action models have achieved remarkable progress in robotic manipulation, yet they suffer from a critical limitation: a lack of 3D scene understanding. This deficiency manifests as three intertwined challenges: weak…

Scene flow estimation is the task of describing 3D motion between temporally successive observations. This thesis aims to build the foundation for building scene flow estimators with two important properties: they are scalable, i.e. they…

Multi-view 3D visual grounding is critical for autonomous driving vehicles to interpret natural languages and localize target objects in complex environments. However, existing datasets and methods suffer from coarse-grained language…

Pre-training on large-scale unlabeled datasets contribute to the model achieving powerful performance on 3D vision tasks, especially when annotations are limited. However, existing rendering-based self-supervised frameworks are…

A point cloud serves as a representation of the surface of a three-dimensional (3D) shape. Deep generative models have been adapted to model their variations typically using a map from a ball-like set of latent variables. However, previous…

Understanding 3D scenes from multi-view inputs has been proven to alleviate the view discrepancy issue in 3D visual grounding. However, existing methods normally neglect the view cues embedded in the text modality and fail to weigh the…