Related papers: PanopticDepth: A Unified Framework for Depth-aware…

Monocular depth estimation is a challenging task that predicts the pixel-wise depth from a single 2D image. Current methods typically model this problem as a regression or classification task. We propose DiffusionDepth, a new approach that…

The realm of Weakly Supervised Instance Segmentation (WSIS) under box supervision has garnered substantial attention, showcasing remarkable advancements in recent years. However, the limitations of box supervision become apparent in its…

Depth estimation is a crucial step for 3D reconstruction with panorama images in recent years. Panorama images maintain the complete spatial information but introduce distortion with equirectangular projection. In this paper, we propose an…

In this paper we tackle the problem of instance-level segmentation and depth ordering from a single monocular image. Towards this goal, we take advantage of convolutional neural nets and train them to directly predict instance-level…

Unified segmentation of 3D point clouds is crucial for scene understanding, but is hindered by its sparse structure, limited annotations, and the challenge of distinguishing fine-grained object classes in complex environments. Existing…

This paper presents a novel framework to integrate both semantic and instance contexts for panoptic segmentation. In existing works, it is common to use a shared backbone to extract features for both things (countable classes such as…

We consider the problem of depth estimation from a single monocular image in this work. It is a challenging task as no reliable depth cues are available, e.g., stereo correspondences, motions, etc. Previous efforts have been focusing on…

Due to the abundance of 2D product images from the Internet, developing efficient and scalable algorithms to recover the missing depth information is central to many applications. Recent works have addressed the single-view depth estimation…

Omnidirectional 3D information is essential for a wide range of applications such as Virtual Reality, Autonomous Driving, Robotics, etc. In this paper, we propose a novel, model-agnostic, two-stage pipeline for omnidirectional monocular…

Perception is crucial for robots that act in real-world environments, as autonomous systems need to see and understand the world around them to act properly. Panoptic segmentation provides an interpretation of the scene by computing a…

The best way to combine the results of deep learning with standard 3D reconstruction pipelines remains an open problem. While systems that pass the output of traditional multi-view stereo approaches to a network for regularisation or…

A fast and accurate panoptic segmentation system for LiDAR point clouds is crucial for autonomous driving vehicles to understand the surrounding objects and scenes. Existing approaches usually rely on proposals or clustering to segment…

State-of-the-art 3D semantic segmentation models are trained on off-the-shelf public benchmarks, but they will inevitably face the challenge of recognition accuracy drop when these well-trained models are deployed to a new domain. In this…

Open-vocabulary panoptic reconstruction offers comprehensive scene understanding, enabling advances in embodied robotics and photorealistic simulation. In this paper, we propose PanopticRecon++, an end-to-end method that formulates panoptic…

Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards. Here, we address three of its most prominent hurdles, namely, i) the adaptation of a single…

DUSt3R has recently shown that one can reduce many tasks in multi-view geometry, including estimating camera intrinsics and extrinsics, reconstructing the scene in 3D, and establishing image correspondences, to the prediction of a pair of…

Segmentation in dense visual scenes poses significant challenges due to occlusions, background clutter, and scale variations. To address this, we introduce PerSense, an end-to-end, training-free, and model-agnostic one-shot framework for…

Panoptic segmentation, which combines instance and semantic segmentation, has gained a lot of attention in autonomous vehicles, due to its comprehensive representation of the scene. This task can be applied for cameras and LiDAR sensors,…

While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects. This limits the use of depth prediction in augmented and virtual…

To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides building an internal representation of the observed scene…