Related papers: Task-Aware 3D Affordance Segmentation via 2D Guida…
Semantic segmentation of remote sensing images is essential for various applications, including vegetation monitoring, disaster management, and urban planning. Previous studies have demonstrated that the self-attention mechanism (SA) is an…
In this paper, we propose a similarity-aware fusion network (SAFNet) to adaptively fuse 2D images and 3D point clouds for 3D semantic segmentation. Existing fusion-based methods achieve remarkable performances by integrating information…
With the emergence of Gaussian Splats, recent efforts have focused on large-scale scene geometric reconstruction. However, most of these efforts either concentrate on memory reduction or spatial space division, neglecting information in the…
Part-aware panoptic segmentation (PPS) requires (a) that each foreground object and background region in an image is segmented and classified, and (b) that all parts within foreground objects are segmented, classified and linked to their…
Class-agnostic 3D instance segmentation tackles the challenging task of segmenting all object instances, including previously unseen ones, without semantic class reliance. Current methods struggle with generalization due to the scarce…
Visual affordance grounding aims to segment all possible interaction regions between people and objects from an image/video, which is beneficial for many applications, such as robot grasping and action recognition. However, existing methods…
Existing 3D semantic segmentation methods rely on point-wise or voxel-wise feature descriptors to output segmentation predictions. However, these descriptors are often supervised at point or voxel level, leading to segmentation models that…
Open-vocabulary 3D affordance detection requires localizing interaction regions on point clouds given novel affordance descriptions. Recent methods extend multimodal large language models (MLLMs) with special output tokens that are decoded…
Temporal action segmentation (TAS) divides untrimmed videos into labeled action segments. While fully supervised methods have advanced the field, challenges such as action variability, ambiguous boundaries, and high annotation costs remain,…
Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data. Especially for LiDAR point clouds, the domain discrepancy becomes…
Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neurel rendering methods as 3D…
An autonomous robot should be able to evaluate the affordances that are offered by a given situation. Here we address this problem by designing a system that can densely predict affordances given only a single 2D RGB image. This is achieved…
Humans excel at learning from expert demonstrations and solving their own problems. To equip intelligent robots and assistants, such as AR glasses, with this ability, it is essential to ground human hand interactions (i.e., affordances)…
Temporal action detection (TAD) is an important yet challenging task in video analysis. Most existing works draw inspiration from image object detection and tend to reformulate it as a proposal generation - classification problem. However,…
Instance shape reconstruction from a 3D scene involves recovering the full geometries of multiple objects at the semantic instance level. Many methods leverage data-driven learning due to the intricacies of scene complexity and significant…
Novel view synthesis has seen significant advancements with 3D Gaussian Splatting (3DGS), enabling real-time photorealistic rendering. However, the inherent fuzziness of Gaussian Splatting presents challenges for 3D scene understanding,…
Understanding object affordances is essential for enabling robots to perform purposeful and fine-grained interactions in diverse and unstructured environments. However, existing approaches either rely on retrieval, which is fragile due to…
Accurate segmentation of tumors and adjacent normal tissues in medical images is essential for surgical planning and tumor staging. Although foundation models generally perform well in segmentation tasks, they often struggle to focus on…
Open-Vocabulary Segmentation (OVS) methods offer promising capabilities in detecting unseen object categories, but the category must be known and needs to be provided by a human, either via a text prompt or pre-labeled datasets, thus…
This paper aims to achieve the segmentation of any 3D part in a scene based on natural language descriptions, extending beyond traditional object-level 3D scene understanding and addressing both data and methodological challenges. Due to…