Related papers: Efficient 3D Instance Mapping and Localization wit…

Large-scale semantic mapping is crucial for outdoor autonomous agents to fulfill high-level tasks such as planning and navigation. This paper proposes a novel method for large-scale 3D semantic reconstruction through implicit…

We propose DistillNeRF, a self-supervised learning framework addressing the challenge of understanding 3D environments from limited 2D observations in outdoor autonomous driving scenes. Our method is a generalizable feedforward model that…

Weakly supervised 3D instance segmentation is essential for 3D scene understanding, especially as the growing scale of data and high annotation costs associated with fully supervised approaches. Existing methods primarily rely on two forms…

3D instance segmentation for laser scanning (LiDAR) point clouds remains a challenge in many remote sensing-related domains. Successful solutions typically rely on supervised deep learning and manual annotations, and consequently focus on…

Masked image modeling (MIM) with transformer backbones has recently been exploited as a powerful self-supervised pre-training technique. The existing MIM methods adopt the strategy to mask random patches of the image and reconstruct the…

Most existing methods realize 3D instance segmentation by extending those models used for 3D object detection or 3D semantic segmentation. However, these non-straightforward methods suffer from two drawbacks: 1) Imprecise bounding boxes or…

This paper introduces Scene-LLM, a 3D-visual-language model that enhances embodied agents' abilities in interactive 3D indoor environments by integrating the reasoning strengths of Large Language Models (LLMs). Scene-LLM adopts a hybrid 3D…

We propose a novel visual re-localization method based on direct matching between the implicit 3D descriptors and the 2D image with transformer. A conditional neural radiance field(NeRF) is chosen as the 3D scene representation in our…

We present NeuralLabeling, a labeling approach and toolset for annotating 3D scenes using either bounding boxes or meshes and generating segmentation masks, affordance maps, 2D bounding boxes, 3D bounding boxes, 6DOF object poses, depth…

We introduce a general, scalable computational framework for multi-axis 3D printing based on implicit neural fields (INFs) that unifies all stages of toolpath generation and global collision-free motion planning. In our pipeline, input…

Recent advances have enabled a single neural network to serve as an implicit scene representation, establishing the mapping function between spatial coordinates and scene properties. In this paper, we make a further step towards continual…

Recent Multi-Modal Large Language Models (MLLMs) have demonstrated strong capabilities in learning joint representations from text and images. However, their spatial reasoning remains limited. We introduce 3DFroMLLM, a novel framework that…

3D instance segmentation is crucial for applications demanding comprehensive 3D scene understanding. In this paper, we introduce a novel method that simultaneously learns coefficients and prototypes. Employing an overcomplete sampling…

Many vision problems require matching images of object instances across different domains. These include fine-grained sketch-based image retrieval (FG-SBIR) and Person Re-identification (person ReID). Existing approaches attempt to learn a…

Recent advances in 3D scene-language understanding have leveraged Large Language Models (LLMs) for 3D reasoning by transferring their general reasoning ability to 3D multi-modal contexts. However, existing methods typically adopt standard…

The neural implicit representation has shown its effectiveness in novel view synthesis and high-quality 3D reconstruction from multi-view images. However, most approaches focus on holistic scene representation yet ignore individual objects…

Deep neural networks have consistently shown great performance in several real-world use cases like autonomous vehicles, satellite imaging, etc., effectively leveraging large corpora of labeled training data. However, learning unbiased…

Semantic segmentation and object detection research have recently achieved rapid progress. However, the former task has no notion of different instances of the same object, and the latter operates at a coarse, bounding-box level. We propose…

Implicit neural representations have emerged as a powerful tool in learning 3D geometry, offering unparalleled advantages over conventional representations like mesh-based methods. A common type of INR implicitly encodes a shape's boundary…

In this paper, we present SegDINO3D, a novel Transformer encoder-decoder framework for 3D instance segmentation. As 3D training data is generally not as sufficient as 2D training images, SegDINO3D is designed to fully leverage 2D…