This paper proposes Wat3R, a cross-domain semi-supervised learning framework for adapting 3D reconstruction models from air to underwater scenes using unlabeled real underwater video footage and a tea…

The paper proposes VLM3, a simple, scalable method that demonstrates standard Vision Language Models (VLMs) can natively learn 3D understanding by focusing on architectural simplicity and specific dat…

The paper proposes MoEIoU, a novel mixture-of-experts based regression loss that adaptively models bounding-box localization errors, achieving superior convergence and accuracy in object detection.

The paper introduces ZipDepth, a compact monocular depth network that achieves high zero-shot accuracy with low computational demands by combining an efficient encoder-decoder and large-scale knowledg…

The paper introduces MetricScenes, a new large-scale, in-the-wild dataset, and demonstrates that fine-tuning existing geometry models on this dataset significantly mitigates the scale-collapse problem…

This paper proposes DPNeXt, a streamlined multi-scale feature fusion decoder for Multi-Task Learning (MTL) in robotics perception systems, improving frozen VFM utilization and mitigating negative indu…

This paper proposes PairGS, a framework for open-vocabulary 3D Gaussian segmentation that models pairwise relations between Gaussians using rich signals from 3D Gaussian representations.

This paper presents a lightweight network for omnidirectional human detection and relative 2D pose estimation from planar LiDAR sequences using Space-Time Blocks.

This paper presents a two-stage recovery approach for camera-only low-cost unmanned ground vehicles to restore guideline tracking when lines are lost.

The paper proposes a novel symmetry-aware, category-level method for 9D object pose estimation that accurately estimates translation and size first, followed by rotation, achieving state-of-the-art re…

The paper proposes xModel-KD, a cross-modal knowledge distillation framework, to improve 3D point cloud segmentation by effectively transferring rich appearance cues from 2D images to sparse 3D geomet…

The paper introduces VLM-IE3D, a framework that enhances 2D vision-language models with implicit and explicit 3D geometries learned from RGB videos, achieving superior performance on various 3D tasks.

This paper introduces VIDAR, a framework for metric dense monocular reconstruction using visual-inertial odometry and Depth Anything 3.

SSR3D-LLM introduces a structured spatial reasoning interface for unified 3D-LLMs, allowing fine-grained object grounding by generating and processing sequential latent spatial steps.

The paper introduces a Mixture-Density Representation (MDA) to model depth ambiguity, effectively eliminating 'flying-point' artifacts at object boundaries by allowing pixels to predict multiple possi…