Related papers: How to Spin an Object: First, Get the Shape Right

We consider a category-level perception problem, where one is given 2D or 3D sensor data picturing an object of a given category (e.g., a car), and has to reconstruct the 3D pose and shape of the object despite intra-class variability…

Learning model-free object pose estimation for unseen instances remains a fundamental challenge in 3D vision. Existing methods typically fall into two disjoint paradigms: category-level approaches predict absolute poses in a canonical space…

Visual correspondence across image-to-image (2D-2D), image-to-point cloud (2D-3D), and point cloud-to-point cloud (3D-3D) geometric matching forms the foundation for numerous 3D vision tasks. Despite sharing a similar problem structure,…

Neural representations have emerged as a new paradigm for applications in rendering, imaging, geometric modeling, and simulation. Compared to traditional representations such as meshes, point clouds, or volumes they can be flexibly…

Monocular 3D object localization in driving scenes is a crucial task, but challenging due to its ill-posed nature. Estimating 3D coordinates for each pixel on the object surface holds great potential as it provides dense 2D-3D geometric…

Synthesizing multi-view 3D from one single image is a significant but challenging task. Zero-1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to the 3D scope. The target view image is generated with a…

Point cloud completion aims to recover partial geometric and topological shapes caused by equipment defects or limited viewpoints. Current methods either solely rely on the 3D coordinates of the point cloud to complete it or incorporate…

We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first develop a fast normalized cuts algorithm.…

Recent advances in Gaussian Splatting based 3D scene representation have shown two major trends: semantics-oriented approaches that focus on high-level understanding but lack explicit 3D geometry modeling, and structure-oriented approaches…

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…

3D structure modeling is essential across scales, enabling applications from fluid simulation and 3D reconstruction to protein folding and molecular docking. Yet, despite shared 3D spatial patterns, current approaches remain fragmented,…

Existing point cloud completion methods, which typically depend on predefined synthetic training datasets, encounter significant challenges when applied to out-of-distribution, real-world scans. To overcome this limitation, we introduce a…

Predicting the pose of objects from a single image is an important but difficult computer vision problem. Methods that predict a single point estimate do not predict the pose of objects with symmetries well and cannot represent uncertainty.…

This paper uses clustering algorithms to introduce a shape framework for deformable objects. Until now, the shape detection of the deformable objects has faced several challenges: 1) unable to form a unified framework for multiple shapes;…

Camera-controllable image editing aims to synthesize novel views of a given scene under varying camera poses while strictly preserving cross-view geometric consistency. However, existing methods typically rely on fragmented geometric…

Perceiving and reconstructing objects from images are critical for real-to-sim transfer tasks, which are widely used in the robotics community. Existing methods rely on multiple submodules such as detection, segmentation, shape…

3D contrastive representation learning has exhibited remarkable efficacy across various downstream tasks. However, existing contrastive learning paradigms based on cosine similarity fail to deeply explore the potential intra-modal…

We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors through a modular, semantically informed design. In vision-based robotic navigation, the…

Object-level manipulation, relocating or reorienting objects in images or videos while preserving scene realism, is central to film post-production, AR, and creative editing. Yet existing methods struggle to jointly achieve three core…

We propose a data-driven 3D shape design method that can learn a generative model from a corpus of existing designs, and use this model to produce a wide range of new designs. The approach learns an encoding of the samples in the training…