Related papers: Formula-Supervised Visual-Geometric Pre-training

Scene understanding from images is a challenging problem encountered in autonomous driving. On the object level, while 2D methods have gradually evolved from computing simple bounding boxes to delivering finer grained results like instance…

Solving image-to-3D from a single view is an ill-posed problem, and current neural reconstruction methods addressing it through diffusion models still rely on scene-specific optimization, constraining their generalization capability. To…

Recent works on 6D object pose estimation focus on learning keypoint correspondences between images and object models, and then determine the object pose through RANSAC-based algorithms or by directly regressing the pose with end-to-end…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…

This paper extensively investigates the effectiveness of synthetic training data to improve the capabilities of vision-and-language models for grounding textual descriptions to image regions. We explore various strategies to best generate…

High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their per-pixel Gaussian prediction paradigm often suffers from…

The significance of informative and robust point representations has been widely acknowledged for 3D scene understanding. Despite existing self-supervised pre-training counterparts demonstrating promising performance, the model collapse and…

Recent research has shown that controllable image generation based on pre-trained GANs can benefit a wide range of computer vision tasks. However, less attention has been devoted to 3D vision tasks. In light of this, we propose a novel…

We investigate transductive zero-shot point cloud semantic segmentation, where the network is trained on seen objects and able to segment unseen objects. The 3D geometric elements are essential cues to imply a novel 3D object type. However,…

Retrospective novel view synthesis (NVS) of dynamic scenes is fundamental to applications such as sports. Recent dynamic 3D Gaussian Splatting (3DGS) approaches introduce temporally coupled formulations to enforce motion coherence across…

3D single object tracking remains a challenging problem due to the sparsity and incompleteness of the point clouds. Existing algorithms attempt to address the challenges in two strategies. The first strategy is to learn dense geometric…

Current point-based approaches encounter limitations in scalability and rendering quality when using large 3D point cloud maps because using them directly for novel view synthesis (NVS) leads to degraded visualizations. We identify the…

Recent advances in mapping techniques have enabled the creation of highly accurate dense 3D maps during robotic missions, such as point clouds, meshes, or NeRF-based representations. These developments present new opportunities for reusing…

A crucial task in scene understanding is 3D object detection, which aims to detect and localize the 3D bounding boxes of objects belonging to specific classes. Existing 3D object detectors heavily rely on annotated 3D bounding boxes during…

Nowadays, pre-training big models on large-scale datasets has become a crucial topic in deep learning. The pre-trained models with high representation ability and transferability achieve a great success and dominate many downstream tasks in…

Current point cloud registration methods are mainly based on local geometric information and usually ignore the semantic information contained in the scenes. In this paper, we treat the point cloud registration problem as a semantic…

Point clouds captured by scanning devices are often incomplete due to occlusion. To overcome this limitation, point cloud completion methods have been developed to predict the complete shape of an object based on its partial input. These…

We present a method to synthesize novel views from a single $360^\circ$ panorama image based on the neural radiance field (NeRF). Prior studies in a similar setting rely on the neighborhood interpolation capability of multi-layer…

Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. However, labeling point cloud data is labor-intensive as it requires human annotators to visualize and inspect the 3D data…

Soft object manipulation tasks in domestic scenes pose a significant challenge for existing robotic skill learning techniques due to their complex dynamics and variable shape characteristics. Since learning new manipulation skills from…