Related papers: SGIFormer: Semantic-guided and Geometric-enhanced …
DETR-based methods, which use multi-layer transformer decoders to refine object queries iteratively, have shown promising performance in 3D indoor object detection. However, the scene point features in the transformer decoder remain fixed,…
As a fundamental task in computer vision, semantic segmentation is widely applied in fields such as autonomous driving, remote sensing image analysis, and medical image processing. In recent years, Transformer-based segmentation methods…
The adoption of Vision Transformers (ViTs) based architectures represents a significant advancement in 3D Medical Image (MI) segmentation, surpassing traditional Convolutional Neural Network (CNN) models by enhancing global contextual…
Panoptic segmentation involves a combination of joint semantic segmentation and instance segmentation, where image contents are divided into two types: things and stuff. We present Panoptic SegFormer, a general framework for panoptic…
Image segmentation is about grouping pixels with different semantics, e.g., category or instance membership, where each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing…
Deep learning techniques have achieved remarkable success in the semantic segmentation of remote sensing images and in land-use change detection. Nevertheless, their real-time deployment on edge platforms remains constrained by decoder…
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…
Vision Transformer has demonstrated impressive success across various vision tasks. However, its heavy computation cost, which grows quadratically with respect to the token sequence length, largely limits its power in handling large feature…
Machine-learning-based surrogate models offer significant computational efficiency and faster simulations compared to traditional numerical methods, especially for problems requiring repeated evaluations of partial differential equations.…
Aligning 3D scene graphs is a crucial initial step for several applications in robot navigation and embodied perception. Current methods in 3D scene graph alignment often rely on single-modality point cloud data and struggle with incomplete…
In this paper, we introduce a data-efficient instance segmentation method we used in the 2021 VIPriors Instance Segmentation Challenge. Our solution is a modified version of Swin Transformer, based on the mmdetection which is a powerful…
Reconstructing dynamic driving scenes from dashcam videos has attracted increasing attention due to its significance in autonomous driving and scene understanding. While recent advances have made impressive progress, most methods still…
Learning representations on large-sized graphs is a long-standing challenge due to the inter-dependence nature involved in massive data points. Transformers, as an emerging class of foundation encoders for graph-structured data, have shown…
Referring image segmentation aims to segment the image region of interest according to the given language expression, which is a typical multi-modal task. Existing methods either adopt the pixel classification-based or the learnable…
Prevalent state-of-the-art instance segmentation methods fall into a query-based scheme, in which instance masks are derived by querying the image feature using a set of instance-aware embeddings. In this work, we devise a new training…
Understanding user intent is essential for situational and context-aware decision-making. Motivated by a real-world scenario, this work addresses intent predictions of smart device users in the vicinity of vehicles by modeling sequential…
Scene text segmentation aims at cropping texts from scene images, which is usually used to help generative models edit or remove texts. The existing text segmentation methods tend to involve various text-related supervisions for better…
Despite significant progress in 3D point cloud segmentation, existing methods primarily address specific tasks and depend on explicit instructions to identify targets, lacking the capability to infer and understand implicit user intentions…
Recently, progress in acquisition equipment such as LiDAR sensors has enabled sensing increasingly spacious outdoor 3D environments. Making sense of such 3D acquisitions requires fine-grained scene understanding, such as constructing…
Point cloud segmentation is a fundamental task in 3D scene understanding. Its progress is constrained by the high cost and time required for dense 3D annotations, making labeled samples difficult to obtain. Beyond annotation scarcity,…