Related papers: Exploring intermediate representation for monocula…

We present a new learning-based framework S-3D-RCNN that can recover accurate object orientation in SO(3) and simultaneously predict implicit rigid shapes from stereo RGB images. For orientation estimation, in contrast to previous studies…

Low-cost autonomous agents including autonomous driving vehicles chiefly adopt monocular 3D object detection to perceive surrounding environment. This paper studies 3D intermediate representation methods which generate intermediate 3D…

6D pose estimation of rigid objects from RGB-D images is crucial for object grasping and manipulation in robotics. Although RGB channels and the depth (D) channel are often complementary, providing respectively the appearance and geometry…

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…

Photometric consistency loss is one of the representative objective functions commonly used for self-supervised monocular depth estimation. However, this loss often causes unstable depth predictions in textureless or occluded regions due to…

We present a deep learning method for end-to-end monocular 3D object detection and metric shape retrieval. We propose a novel loss formulation by lifting 2D detection, orientation, and scale estimation into 3D space. Instead of optimizing…

Estimating the 3D position and orientation of objects in the environment with a single RGB camera is a critical and challenging task for low-cost urban autonomous driving and mobile robots. Most of the existing algorithms are based on the…

We present an approach for reconstructing vehicles from a single (RGB) image, in the context of autonomous driving. Though the problem appears to be ill-posed, we demonstrate that prior knowledge about how 3D shapes of vehicles project to…

In this paper, we propose a monocular 3D object detection framework in the domain of autonomous driving. Unlike previous image-based methods which focus on RGB feature extracted from 2D images, our method solves this problem in the…

In recent years, there is an influx of deep learning models for 3D vehicle object detection. However, little attention was paid to orientation prediction. Existing research work proposed various vehicle orientation representation methods…

We propose a real-time RGB-based pipeline for object detection and 6D pose estimation. Our novel 3D orientation estimation is based on a variant of the Denoising Autoencoder that is trained on simulated views of a 3D model using Domain…

3D object detection and dense depth estimation are one of the most vital tasks in autonomous driving. Multiple sensor modalities can jointly attribute towards better robot perception, and to that end, we introduce a method for jointly…

Current geometry-based monocular 3D object detection models can efficiently detect objects by leveraging perspective geometry, but their performance is limited due to the absence of accurate depth information. Though this issue can be…

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video.…

A self-driving perception model aims to extract 3D semantic representations from multiple cameras collectively into the bird's-eye-view (BEV) coordinate frame of the ego car in order to ground downstream planner. Existing perception methods…

Current approaches to semantic image and scene understanding typically employ rather simple object representations such as 2D or 3D bounding boxes. While such coarse models are robust and allow for reliable object detection, they discard…

3D object detection is an essential task in autonomous driving. Recent techniques excel with highly accurate detection rates, provided the 3D input data is obtained from precise but expensive LiDAR technology. Approaches based on cheaper…

Shape implicit neural representations (INRs) have recently shown to be effective in shape analysis and reconstruction tasks. Existing INRs require point coordinates to learn the implicit level sets of the shape. When a normal vector is…

Accurate localization of other traffic participants is a vital task in autonomous driving systems. State-of-the-art systems employ a combination of sensing modalities such as RGB cameras and LiDARs for localizing traffic participants, but…

Accurate 6D object pose estimation is fundamental to robotic manipulation and grasping. Previous methods follow a local optimization approach which minimizes the distance between closest point pairs to handle the rotation ambiguity of…