23 accepted papers
In this paper, we propose BuildingGPT, a novel auto-regressive model for building wireframe reconstruction from point clouds with reinforcement learning.Unlike prior works based on detection or diffusion models, BuildingGPT reformulates the building wireframe reconstruction task into a sequence pred
Multimodal SLAM is an important topic in 3D computer vision research. Recent visual-LiDAR SLAM systems use photometric error for camera pose estimation, but their use of sparse LiDAR projections underutilizes image information. Integrating 3D Gaussian Splatting allows full image rendering, but the e
While structure-based relocalizers have long strived for point correspondences when establishing or regressing query-map associations, in this paper, we pioneer the use of planar primitives and 3D planar maps for lightweight 6-DoF camera relocalization in structured environments. Planar primitives,
Recently, diffusion policy models have been applied in the field of robotics. Most existing methods use all observations as condition inputs to the diffusion model. With the denoising of the diffusion model, Gaussian noise gradually becomes an action sequence. However, since these constraints are im
In this paper, we present BWFormer, a novel Transformer-based model for building wireframe reconstruction from airborne LiDAR point cloud. The problem is solved in a ground-up manner here by detecting the building corners in 2D, lifting and connecting them in 3D space afterwards with additional dat…
Monocular image-goal navigation in an outdoor environment is a challenging task. Robots have to face monocular scale uncertainty and complex environments. Recently, implementations based on imitation learning have made significant progress. However, robots tend to focus too much on the current state
This paper proposes a multi-view collaborative matching strategy for reliable track construction in complex scenarios. We observe that the pairwise matching paradigms applied to image set matching often result in ambiguous estimation when the selected independent pairs exhibit significant occlusions…
Multi-camera systems are increasingly vital in the environmental perception of autonomous vehicles and robotics. Their physical configuration offers inherent fixed relative pose constraints that benefit Structure-from-Motion (SfM). However, traditional global SfM systems struggle with robustness due…
3D maps assembled from planar primitives are compact and expressive in representing man-made environments. In this paper, we present **NeuralPlane**, a novel approach that explores **neural** fields for multi-view 3D **plane** reconstruction. Our method is centered upon the core idea of distilling g…
We propose Quadratic Gaussian Splatting (QGS), a novel representation that replaces static primitives with deformable quadric surfaces (e.g., ellipse, paraboloids) to capture intricate geometry. Unlike prior works that rely on Euclidean distance for primitive density modeling--a metric misaligned wi…
In this paper, we propose a new image-based visual place recognition (VPR) framework by exploiting the structural cues in bird’s-eye view (BEV) from a single monocular camera. The motivation arises from two key observations about place recognition methods based on both appearance and structure: 1) F
"This paper proposes a side-view context inpainting strategy (SidePaint) to ease the reasoning of unknown 3D patterns for semantic scene completion. Based on the observation that the learning burden on pattern completion increases with spatial complexity and feature sparsity, the SidePaint strategy…
Visual localization, also known as camera pose estimation, is a crucial component of many applications, such as robotics, autonomous driving, and augmented reality. Traditional visual localization algorithms typically run on point cloud maps generated by algorithms such as Structure-from-Motion (SfM
Scaled relative pose estimation i.e. estimating relative rotation and scaled relative translation between two images has always been a major challenge in global Structure-from-Motion (SfM). This difficulty arises because the two-view relative translation computed by traditional geometric vision meth…
Global translation estimation is a highly challenging step in the global structure from motion (SfM) algorithm. Many existing methods depend solely on relative translations leading to inaccuracies in low parallax scenes and degradation under collinear camera motion. While recent approaches aim to ad…
Neural implicit representation of geometric shapes has witnessed considerable advancements in recent years. However common distance field based implicit representations specifically signed distance field (SDF) for watertight shapes or unsigned distance field (UDF) for arbitrary shapes routinely suff…
This paper proposes a shape anchor guided learning strategy (AncLearn) for robust holistic indoor scene understanding. We observe that the search space constructed by current methods for proposal feature grouping and instance point sampling often introduces massive noise to instance detection and me…
In order to fully perceive the surrounding environment, many intelligent robots and self-driving cars are equipped with a multi-camera system. Based on this system, the structure-from-motion (SfM) technology is used to realize scene reconstruction, but the fixed relative poses between cameras in the…
Multiple sensors, especially cameras and LiDARs, are widely used in autonomous vehicles. In order to fuse data from different sensors accurately, precise calibrations are required, including camera intrinsic parameters, and relative poses between multiple cameras and LiDARs. However, most existing c…
Estimating the 6-DoF camera pose of an image with respect to a 3D scene model, known as visual localization, is a fundamental problem in many computer vision and robotics tasks. Among various visual localization methods, the direct 2D-3D matching method has become the preferred method for many pract…
Compared to widely used LiDAR-based mapping in autonomous driving field, image-based mapping method has the advantages of low cost, high resolution, and no need for complex calibration. However, the image-based 3D mapping depends heavily on the texture richness and always leaves holes and outliers i…
In this paper we present an effcient modeling framework for large scale urban scenes. Taking surface meshes derived from multi- view-stereo systems as input, our algorithm outputs simplied models with semantics at different levels of detail (LODs). Our key observation is that urban building is usual…
Structure-from-Motion (SfM) methods can be broadly categorized as incremental or global according to their ways to estimate initial camera poses. While incremental system has advanced in robustness and accuracy, the efficiency remains its key challenge. To solve this problem, global reconstruction s…