Related papers: PointAlign: Feature-Level Alignment Regularization…
Multimodal Large Language Models (MLLMs) have excelled in 2D image-text comprehension and image generation, but their understanding of the 3D world is notably deficient, limiting progress in 3D language understanding and generation. To…
Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging implicit geometric priors from 3D reconstruction models,…
Feature matching is a fundamental problem in computer vision with wide-ranging applications, including simultaneous localization and mapping (SLAM), image stitching, and 3D reconstruction. While recent advances in deep learning have…
Decades of cognitive science establish that humans navigate environments by forming cognitive maps, defined as allocentric and topology-preserving representations of 3D space. While modern Vision-Language Models (VLMs) demonstrate emergent…
Self-supervised representation learning for point cloud has demonstrated effectiveness in improving pre-trained model performance across diverse tasks. However, as pre-trained models grow in complexity, fully fine-tuning them for downstream…
Point cloud is a collection of 3D coordinates that are discrete geometric samples of an object's 2D surfaces. Imperfection in the acquisition process means that point clouds are often corrupted with noise. Building on recent advances in…
Object detection through either RGB images or the LiDAR point clouds has been extensively explored in autonomous driving. However, it remains challenging to make these two data sources complementary and beneficial to each other. In this…
Change detection from traditional \added{2D} optical images has limited capability to model the changes in the height or shape of objects. Change detection using 3D point cloud \added{from photogrammetry or LiDAR surveying} can fill this…
Understanding visual degradations is a critical yet challenging problem in computer vision. While recent Vision-Language Models (VLMs) excel at qualitative description, they often fall short in understanding the parametric physics…
Fusion of 2D images and 3D point clouds is important because information from dense images can enhance sparse point clouds. However, fusion is challenging because 2D and 3D data live in different spaces. In this work, we propose MVPNet…
The demand for semantically rich 3D models of indoor scenes is rapidly growing, driven by applications in augmented reality, virtual reality, and robotics. However, creating them from sparse views remains a challenge due to geometric…
Point-Vision-Language Models promise to empower embodied agents with executable spatial reasoning, yet they frequently succumb to geometric hallucination where predicted 3D structures contradict the observed 2D reality. We identify a key…
Recent generalist vision-language models (VLMs) have demonstrated impressive reasoning capabilities across diverse multimodal tasks. However, these models still struggle with fine-grained object-level understanding and grounding. In terms…
Vision-language model (VLM) fine-tuning for application-specific visual grounding based on natural language instructions has become one of the most popular approaches for learning-enabled autonomous systems. However, such fine-tuning relies…
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…
The ability for robots to comprehend and execute manipulation tasks based on natural language instructions is a long-term goal in robotics. The dominant approaches for language-guided manipulation use 2D image representations, which face…
PointNet has recently emerged as a popular representation for unstructured point cloud data, allowing application of deep learning to tasks such as object detection, segmentation and shape completion. However, recent works in literature…
We tackle the problem of 3D point cloud localization based on a few natural linguistic descriptions and introduce a novel neural network, Text2Loc, that fully interprets the semantic relationship between points and text. Text2Loc follows a…
Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation. Unlike classical optimization-based methods, recent learning-based methods leverage the power of deep learning for…
Recent advances in generative artificial intelligence have enabled the creation of highly realistic image forgeries, raising significant concerns about digital media authenticity. While existing detection methods demonstrate promising…