Related papers: Formula-Supervised Visual-Geometric Pre-training
Learning to autonomously assemble shapes is a crucial skill for many robotic applications. While the majority of existing part assembly methods focus on correctly posing semantic parts to recreate a whole object, we interpret assembly more…
Deep learning techniques for point clouds have achieved strong performance on a range of 3D vision tasks. However, it is costly to annotate large-scale point sets, making it critical to learn generalizable representations that can transfer…
Learning-based 3D reconstruction models, represented by Visual Geometry Grounded Transformers (VGGTs), have made remarkable progress with the use of large-scale transformers. Their prohibitive computational and memory costs severely hinder…
Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing imagery according to natural language expressions. Previous methods typically rely on sentence-level vision-language alignment, which struggles to exploit…
The success of supervised learning requires large-scale ground truth labels which are very expensive, time-consuming, or may need special skills to annotate. To address this issue, many self- or un-supervised methods are developed. Unlike…
Cross-view geo-spatial learning consists of two important tasks: Cross-View Geo-Localization (CVGL) and Cross-View Image Synthesis (CVIS), both of which rely on establishing geometric correspondences between ground and aerial views. Recent…
3D Visual Grounding (3DVG) involves localizing target objects in 3D point clouds based on natural language. While prior work has made strides using textual descriptions, leveraging spoken language-known as Audio-based 3D Visual…
In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks. However, when extended to…
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…
A current limitation of video generative video models is that they generate plausible looking frames, but poor motion -- an issue that is not well captured by FVD and other popular methods for evaluating generated videos. Here we go beyond…
Scene Graph Generation (SGG) aims to extract entities, predicates and their semantic structure from images, enabling deep understanding of visual content, with many applications such as visual reasoning and image retrieval. Nevertheless,…
In this paper, we propose an efficient multi-level convolution architecture for 3D visual grounding. Conventional methods are difficult to meet the requirements of real-time inference due to the two-stage or point-based architecture.…
Integrating visual features has been proved useful for natural language understanding tasks. Nevertheless, in most existing multimodal language models, the alignment of visual and textual data is expensive. In this paper, we propose a novel…
Recent text-to-image models, such as Stable Diffusion, have achieved impressive visual quality, yet they often suffer from geometric inconsistencies that undermine the structural realism of generated scenes. One prominent issue is vanishing…
Learning robust and generalizable manipulation skills from demonstrations remains a key challenge in robotics, with broad applications in industrial automation and service robotics. While recent imitation learning methods have achieved…
Spatial intelligence requires visual representations that capture both semantic objects and geometric structure in the physical world. To support this, two major pre-training schemes are now widely used as foundation backbones:…
Visual Place Recognition (VPR) has been traditionally formulated as a single-image retrieval task. Using multiple views offers clear advantages, yet this setting remains relatively underexplored and existing methods often struggle to…
3D Gaussian Splatting (3DGS) enables efficient rendering, yet accurate surface reconstruction remains challenging due to unreliable geometric supervision. Existing approaches predominantly rely on depth-based reprojection to infer…
Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for applications in embodied AI and remote collaboration. This task is exceptionally difficult…
Self-supervised vision-and-language pretraining (VLP) aims to learn transferable multi-modal representations from large-scale image-text data and to achieve strong performances on a broad scope of vision-language tasks after finetuning.…