Related papers: Aether: Geometric-Aware Unified World Modeling
A key challenge in artificial intelligence and neuroscience is understanding how neural systems learn representations that capture the underlying dynamics of the world. Most world models represent the transition function with unstructured…
Visual grounding in 3D is the key for embodied agents to localize language-referred objects in open-world environments. However, existing benchmarks are limited to indoor focus, single-platform constraints, and small scale. We introduce…
We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors through a modular, semantically informed design. In vision-based robotic navigation, the…
Artificial intelligence for scientific discovery has recently generated significant interest within the machine learning and scientific communities, particularly in the domains of chemistry, biology, and material discovery. For these…
We present UniQueR, a unified query-based feedforward framework for efficient and accurate 3D reconstruction from unposed images. Existing feedforward models such as DUSt3R, VGGT, and AnySplat typically predict per-pixel point maps or…
In this paper, we propose AUKAI, an Adaptive Unified Knowledge-Action Intelligence for embodied cognition that seamlessly integrates perception, memory, and decision-making via multi-scale error feedback. Interpreting AUKAI as an embedded…
Bayesian learning with Gaussian processes demonstrates encouraging regression and classification performances in solving computer vision tasks. However, Bayesian methods on 3D manifold-valued vision data, such as meshes and point clouds,…
Recent advancements in 3D reconstruction and neural rendering have enhanced the creation of high-quality digital assets, yet existing methods struggle to generalize across varying object shapes, textures, and occlusions. While Next Best…
Geometry problem solving (GPS) represents a critical frontier in artificial intelligence, with profound applications in education, computer-aided design, and computational graphics. Despite its significance, automating GPS remains…
This paper presents Omni-View, which extends the unified multimodal understanding and generation to 3D scenes based on multiview images, exploring the principle that "generation facilitates understanding". Consisting of understanding model,…
Geometric diffusion models have shown remarkable success in molecular dynamics and structure generation. However, efficiently fine-tuning them for downstream tasks with varying geometric controls remains underexplored. In this work, we…
In the majority of executive domains, a notion of normality is involved in most strategic decisions. However, few data-driven tools that support strategic decision-making are available. We introduce and extend the use of autoencoders to…
Multi-Task Learning (MTL) seeks to boost statistical power and learning efficiency by discovering structure shared across related tasks. State-of-the-art MTL representation methods, however, usually treat the latent representation matrix as…
Recent feed-forward models have significantly advanced geometry perception for inferring dense 3D structure from sensor observations. However, its essential capabilities remain fragmented across multiple incompatible paradigms, including…
Open-vocabulary panoptic reconstruction is essential for advanced robotics perception and simulation. However, existing methods based on 3D Gaussian Splatting (3DGS) often struggle to simultaneously achieve geometric accuracy, coherent…
3D-aware image synthesis aims at learning a generative model that can render photo-realistic 2D images while capturing decent underlying 3D shapes. A popular solution is to adopt the generative adversarial network (GAN) and replace the…
Simultaneous understanding and 3D reconstruction plays an important role in developing end-to-end embodied intelligent systems. To achieve this, recent approaches resort to 2D-to-3D feature alignment paradigm, which leads to limited 3D…
NeRFs have achieved incredible success in novel view synthesis. However, the accuracy of the implicit geometry is unsatisfactory because the passive static environmental illumination has low spatial frequency and cannot provide enough…
Modern monocular 3D reconstruction methods and vision-language models (VLMs) demonstrate impressive results on standard benchmarks, yet recent works cast doubt on their true understanding of geometric properties. We introduce GOQ, a…
We introduce the first learning-based dense matching algorithm, termed Equirectangular Projection-Oriented Dense Kernelized Feature Matching (EDM), specifically designed for omnidirectional images. Equirectangular projection (ERP) images,…