Related papers: ViewSRD: 3D Visual Grounding via Structured Multi-…

Open-vocabulary 3D object detection (OV-3DDet) aims to localize and recognize both seen and previously unseen object categories within any new 3D scene. While language and vision foundation models have achieved success in handling various…

Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention…

3D visual grounding aims to identify objects in 3D point cloud scenes that match specific natural language descriptions. This requires the model to not only focus on the target object itself but also to consider the surrounding environment…

Recent advancements in Vision Language Models (VLMs) have demonstrated remarkable promise in generating visually grounded responses. However, their application in the medical domain is hindered by unique challenges. For instance, most VLMs…

The ability to interpret and comprehend a 3D scene is essential for many vision and robotics systems. In numerous applications, this involves 3D object detection, i.e.~identifying the location and dimensions of objects belonging to a…

Segment matching is an important intermediate task in computer vision that establishes correspondences between semantically or geometrically coherent regions across images. Unlike keypoint matching, which focuses on localized features,…

Visual grounding seeks to localize the image region corresponding to a free-form text description. Recently, the strong multimodal capabilities of Large Vision-Language Models (LVLMs) have driven substantial improvements in visual…

We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck. For example, the grounding process is usually a trivial language-location…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Scene understanding and reasoning has been a fundamental problem in 3D computer vision, requiring models to identify objects, their properties, and spatial or comparative relationships among the objects. Existing approaches enable this by…

Progress in 3D vision-language learning has been hindered by the scarcity of large-scale 3D datasets. We introduce UniVLG, a unified architecture for 2D and 3D vision-language understanding that bridges the gap between existing 2D-centric…

Multimodal summarization requires models to jointly understand textual and visual inputs to generate concise, semantically coherent summaries. Existing methods often inject shallow visual features into deep language models, leading to…

Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with only a few sparse RGB views and strict latency constraints.…

Low-resolution (LR) multi-view capture limits the fidelity of 3D Gaussian Splatting (3DGS). 3DGS super-resolution (SR) is therefore important, yet challenging because it must recover missing high-frequency details while enforcing cross-view…

Understanding 3D scenes goes beyond simply recognizing objects; it requires reasoning about the spatial and semantic relationships between them. Current 3D scene-language models often struggle with this relational understanding,…

Taking an image of an object is at its core a lossy process. The rich information about the three-dimensional structure of the world is flattened to an image plane and decisions such as viewpoint and camera parameters are final and not…

Spatio-temporal video grounding aims to retrieve the spatio-temporal tube of a queried object according to the given sentence. Currently, most existing grounding methods are restricted to well-aligned segment-sentence pairs. In this paper,…

Pretrained vision-language models, such as CLIP, have demonstrated strong generalization capabilities, making them promising tools in the realm of zero-shot visual recognition. Visual relation detection (VRD) is a typical task that…

Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging. In this paper, we propose a new model, named InstanceRefer, to achieve a superior 3D visual grounding…

Three-dimensional (3D) object reconstruction based on differentiable rendering (DR) is an active research topic in computer vision. DR-based methods minimize the difference between the rendered and target images by optimizing both the shape…