Related papers: Mask4Former: Mask Transformer for 4D Panoptic Segm…

We propose a new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance. The proposed network, built upon submanifold…

Indoor environments evolve as objects move, appear, or leave the scene. Capturing these dynamics requires maintaining temporally consistent instance identities across intermittently captured 3D scans, even when changes are unobserved. We…

We present TubeFormer-DeepLab, the first attempt to tackle multiple core video segmentation tasks in a unified manner. Different video segmentation tasks (e.g., video semantic/instance/panoptic segmentation) are usually considered as…

Multi-task networks can potentially improve performance and computational efficiency compared to single-task networks, facilitating online deployment. However, current multi-task architectures in point cloud perception combine multiple…

With the rapid advances of autonomous driving, it becomes critical to equip its sensing system with more holistic 3D perception. However, existing works focus on parsing either the objects (e.g. cars and pedestrians) or scenes (e.g. trees…

Anticipating future events is an important prerequisite towards intelligent behavior. Video forecasting has been studied as a proxy task towards this goal. Recent work has shown that to predict semantic segmentation of future frames,…

In this paper, we propose PolyTransform, a novel instance segmentation algorithm that produces precise, geometry-preserving masks by combining the strengths of prevailing segmentation approaches and modern polygon-based methods. In…

Transformer-based methods have become the dominant approach for 3D instance segmentation. These methods predict instance masks via instance queries, ranking them by classification confidence and IoU scores to select the top prediction as…

LiDAR-based 3D scene perception is a fundamental and important task for autonomous driving. Most state-of-the-art methods on LiDAR-based 3D recognition tasks focus on single frame 3D point cloud data, and the temporal information is ignored…

This paper presents an end-to-end instance segmentation framework, termed SOIT, that Segments Objects with Instance-aware Transformers. Inspired by DETR \cite{carion2020end}, our method views instance segmentation as a direct set prediction…

We present OSFormer, the first one-stage transformer framework for camouflaged instance segmentation (CIS). OSFormer is based on two key designs. First, we design a location-sensing transformer (LST) to obtain the location label and…

Image segmentation is often ambiguous at the level of individual image patches and requires contextual information to reach label consensus. In this paper we introduce Segmenter, a transformer model for semantic segmentation. In contrast to…

Open-vocabulary 3D instance segmentation is a core capability for robotics and AR/VR, but prior methods trade one bottleneck for another: multi-stage 2D+3D pipelines aggregate foundation-model outputs at hundreds of seconds per scene, while…

Universal Image Segmentation is not a new concept. Past attempts to unify image segmentation in the last decades include scene parsing, panoptic segmentation, and, more recently, new panoptic architectures. However, such panoptic…

Sliding-window object detectors that generate bounding-box object predictions over a dense, regular grid have advanced rapidly and proven popular. In contrast, modern instance segmentation approaches are dominated by methods that first…

Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…

Segmenting object instances is a key task in machine perception, with safety-critical applications in robotics and autonomous driving. We introduce a novel approach to instance segmentation that jointly leverages measurements from multiple…

Amodal Instance Segmentation (AIS) aims to segment the region of both visible and possible occluded parts of an object instance. While Mask R-CNN-based AIS approaches have shown promising results, they are unable to model high-level…

Coarse-to-fine 3D instance segmentation methods show weak performances compared to recent Grouping-based, Kernel-based and Transformer-based methods. We argue that this is due to two limitations: 1) Instance size overestimation by…

Building accurate maps is a key building block to enable reliable localization, planning, and navigation of autonomous vehicles. We propose a novel approach for building accurate maps of dynamic environments utilizing a sequence of LiDAR…