相关论文: UniFunc3D: Unified Active Spatial-Temporal Groundi…

3D vision-language (VL) reasoning has gained significant attention due to its potential to bridge the 3D physical world with natural language descriptions. Existing approaches typically follow task-specific, highly specialized paradigms.…

Despite recent advances in multimodal content generation enabled by vision-language models (VLMs), their ability to reason about and generate structured 3D scenes remains largely underexplored. This limitation constrains their utility in…

Grounding natural language in 3D environments is a critical step toward achieving robust 3D vision-language alignment. Current datasets and models for 3D visual grounding predominantly focus on identifying and localizing objects from…

Vision-Language Models (VLMs) have enabled autonomous GUI agents that translate natural language instructions into executable screen coordinates. However, grounding performance degrades in high-resolution interfaces, where dense layouts and…

Although perception systems have made remarkable advancements in recent years, particularly in 2D reasoning segmentation, these systems still rely on explicit human instruction or pre-defined categories to identify target objects before…

Recent success of vision foundation models have shown promising performance for the 2D perception tasks. However, it is difficult to train a 3D foundation network directly due to the limited dataset and it remains under explored whether…

The concept of 3D scene graphs is increasingly recognized as a powerful semantic and hierarchical representation of the environment. Current approaches often address this at a coarse, object-level resolution. In contrast, our goal is to…

Fine-grained 3D part segmentation is crucial for enabling embodied AI systems to perform complex manipulation tasks, such as interacting with specific functional components of an object. However, existing interactive segmentation methods…

The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or…

Prompt-driven image analysis converts a single natural-language instruction into multiple steps: locate, segment, edit, and describe. We present a practical case study of a unified pipeline that combines open-vocabulary detection,…

Open-vocabulary, task-oriented grasping of specific functional parts, particularly with dual arms, remains a key challenge, as current Vision-Language Models (VLMs), while enhancing task understanding, often struggle with precise grasp…

While large-scale image-text pretrained models such as CLIP have been used for multiple video-level tasks on trimmed videos, their use for temporal localization in untrimmed videos is still a relatively unexplored task. We design a new…

Native unified multimodal models, which integrate both generative and understanding capabilities, face substantial computational overhead that hinders their real-world deployment. Existing acceleration techniques typically employ a static,…

Computer vision is largely based on 2D techniques, with 3D vision still relegated to a relatively narrow subset of applications. However, by building on recent advances in 3D models such as neural radiance fields, some authors have shown…

Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge. This is mainly because generic category-specified VS tasks need to detect all objects and track them…

3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the…

We introduce the first approach to solve the challenging problem of unsupervised 4D visual scene understanding for complex dynamic scenes with multiple interacting people from multi-view video. Our approach simultaneously estimates a…

Existing state-of-the-art 3D point cloud understanding methods merely perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework that simultaneously solves the downstream high-level…

This paper aims to achieve universal segmentation of arbitrary semantic level. Despite significant progress in recent years, specialist segmentation approaches are limited to specific tasks and data distribution. Retraining a new model for…

During interactive segmentation, a model and a user work together to delineate objects of interest in a 3D point cloud. In an iterative process, the model assigns each data point to an object (or the background), while the user corrects…