We introduce a self-supervised framework for learning joint visuospatial representations from RGB-D observations. While modern vision foundation models are trained almost exclusively on RGB images, ma...
arXiv:2608.23850v1 Announce Type: new Abstract: Foundational visual features such as DINO have played a critical role across modern computer vision, and have recently become key components in multi-v...
arXiv:2512. 16919v2 Announce Type: replace-cross Abstract: Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving.
arXiv:2607. 21595v1 Announce Type: cross Abstract: Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning.
arXiv:2608.20788v1 Announce Type: new Abstract: Deep learning-based Multi-View Stereo (MVS) has advanced significantly but often generalizes poorly to unseen scenes, particularly in occluded areas or...
arXiv:2503. 19947v2 Announce Type: replace-cross Abstract: Generalized metric depth understanding is critical for precise vision-guided robotics, which current state-of-the-art (SOTA) vision-encoders do not support.
arXiv:2607. 12433v1 Announce Type: cross Abstract: Diffusion models have recently become the dominant paradigm for monocular depth estimation (MDE).
arXiv:2608.21136v1 Announce Type: new Abstract: Recently, open-vocabulary zero-shot 3D scene understanding using vision foundation models has emerged as a promising alternative to data-intensive supe...
arXiv:2601. 11729v2 Announce Type: replace-cross Abstract: Visual Foundation Models (VFMs), such as DINO and CLIP, excel in semantic understanding of images but exhibit limited spatial reasoning capabilities, which limits their applicability to embodied systems.
arXiv:2604. 02546v3 Announce Type: replace-cross Abstract: Pretraining 3D encoders through alignment with Contrastive Language-Image Pre-training (CLIP) has emerged as a promising direction for learning generalizable representations for 3D scene understanding.
arXiv:2601. 23286v4 Announce Type: replace-cross Abstract: While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift.
Multimodal Large Language Models (MLLMs) excel at 2D semantic understanding but lack intrinsic 3D awareness, resulting in representations that fail to maintain geometric and spatial consistency across video frames. Given the scarcity of large-scale 3D data, we present GeoVR, a novel framework that learns geometric representations using purely 2D video sequences.