Related papers: MonoDiff9D: Monocular Category-Level 9D Object Pos…

Monocular 3D object detection (Mono3D) aims to infer object locations and dimensions in 3D space from a single RGB image. Despite recent progress, existing methods remain highly sensitive to camera intrinsics and struggle to generalize…

Monocular 3D object detection aims to localize 3D bounding boxes in an input single 2D image. It is a highly challenging problem and remains open, especially when no extra information (e.g., depth, lidar and/or multi-frames) can be…

Denoising diffusion probabilistic models that were initially proposed for realistic image generation have recently shown success in various perception tasks (e.g., object detection and image segmentation) and are increasingly gaining…

In this paper, we introduce a novel single shot approach for 6D object pose estimation of rigid objects based on depth images. For this purpose, a fully convolutional neural network is employed, where the 3D input data is spatially…

Object pose estimation is crucial to robotic perception and typically provides a single-pose estimate. However, a single estimate cannot capture pose uncertainty deriving from visual ambiguity, which can lead to unreliable behavior.…

6D pose estimation of textureless objects is a valuable but challenging task for many robotic applications. In this work, we propose a framework to address this challenge using only RGB images acquired from multiple viewpoints. The core…

This paper proposes a universal framework, called OVE6D, for model-based 6D object pose estimation from a single depth image and a target object mask. Our model is trained using purely synthetic data rendered from ShapeNet, and, unlike most…

Generating realistic 3D scenes is an area of growing interest in computer vision and robotics. However, creating high-quality, diverse synthetic 3D content often requires expert intervention, making it costly and complex. Recently, efforts…

Monocular depth estimation is a fundamental yet challenging task in computer vision, especially under complex conditions such as textureless surfaces, transparency, and specular reflections. Recent diffusion-based approaches have…

Robots and other smart devices need efficient object-based scene representations from their on-board vision systems to reason about contact, physics and occlusion. Recognized precise object models will play an important role alongside…

This paper presents PolyDiffuse, a novel structured reconstruction algorithm that transforms visual sensor data into polygonal shapes with Diffusion Models (DM), an emerging machinery amid exploding generative AI, while formulating…

We address the problem of learning accurate 3D shape and camera pose from a collection of unlabeled category-specific images. We train a convolutional network to predict both the shape and the pose from a single image by minimizing the…

We study the 3D object understanding task for manipulating everyday objects with different material properties (diffuse, specular, transparent and mixed). Existing monocular and RGB-D methods suffer from scale ambiguity due to missing or…

Current 4D generation methods have achieved noteworthy efficacy with the aid of advanced diffusion generative models. However, these methods lack multi-view spatial-temporal modeling and encounter challenges in integrating diverse prior…

Cluttered bin-picking environments are challenging for pose estimation models. Despite the impressive progress enabled by deep learning, single-view RGB pose estimation models perform poorly in cluttered dynamic environments. Imbuing the…

We present a method to infer 3D pose and shape of vehicles from a single image. To tackle this ill-posed problem, we optimize two-scale projection consistency between the generated 3D hypotheses and their 2D pseudo-measurements.…

In this work, we present PoIFusion, a conceptually simple yet effective multi-modal 3D object detection framework to fuse the information of RGB images and LiDAR point clouds at the points of interest (PoIs). Different from the most…

We propose DiffusionDet, a new framework that formulates object detection as a denoising diffusion process from noisy boxes to object boxes. During the training stage, object boxes diffuse from ground-truth boxes to random distribution, and…

Reconstructing the 3D shape of an object from a single RGB image is a long-standing and highly challenging problem in computer vision. In this paper, we propose a novel method for single-image 3D reconstruction which generates a sparse…

3D object detection is vital as it would enable us to capture objects' sizes, orientation, and position in the world. As a result, we would be able to use this 3D detection in real-world applications such as Augmented Reality (AR),…