3D Vision

ZOPP: A groundbreaking framework for zero-shot offboard panoptic perception in autonomous driving, enabling high-quality 3D scene understanding without human labeling.

Zero-shot 3D scene reconstruction from single images is achieved by assembling diverse deep priors from large models, eliminating the need for 3D/2D training data and achieving superior performance.

Zero-shot Event-Intensity Asymmetric Stereo (ZEST) uses visual prompting and monocular cues to achieve robust 3D perception without event-specific training, outperforming existing methods.

X-Ray: A novel 3D representation generating complete object surfaces from a single image!

WildGaussians enhances 3D Gaussian splatting for real-time rendering of photorealistic 3D scenes from in-the-wild images featuring occlusions and appearance changes.

Wild-GS achieves real-time novel view synthesis from unconstrained photos by efficiently adapting 3D Gaussian Splatting, significantly improving speed and quality over existing methods.

VQ-Map leverages vector quantization to estimate bird’s-eye-view maps with unprecedented accuracy, setting new benchmarks.

VPNet, a novel semantic scene completion network, uses multi-frame knowledge distillation and confident voxel proposals to improve accuracy and handle dynamic aspects of 3D scenes from point clouds, a…

Voxel Mamba: a group-free 3D object detection method using state space models, achieving higher accuracy and efficiency by overcoming limitations of serialization-based Transformers.

VFM-6D: a novel framework achieving generalizable object pose estimation for unseen categories by leveraging vision-language models.

VCR-GauS: Novel view-consistent depth-normal regularizer for superior, real-time 3D surface reconstruction using Gaussian splatting.

New uncertainty estimation method for 3D Gaussian Splatting improves scene reconstruction quality by leveraging variational multi-scale representation and efficiently removing noisy data.

UV3-TeD generates high-quality 3D textures directly on object surfaces using a novel diffusion probabilistic model, eliminating UV-mapping limitations.

New unlearnable framework secures 3D point cloud data by using class-wise transformations, enabling authorized training while preventing unauthorized access.

UniSDF: Unifying neural representations reconstructs complex scenes with reflections, achieving state-of-the-art performance by blending camera and reflected view radiance fields.

Unique3D: Single image to high-fidelity 3D mesh in 30 seconds!

Unified Domain Generalization and Adaptation (UDGA) tackles 3D object detection’s domain adaptation challenges by leveraging multi-view overlap and label-efficient learning, achieving state-of-the-art…

UniDSeg uses Visual Foundation Models to create a unified framework for adaptable and generalizable cross-domain 3D semantic segmentation, achieving state-of-the-art results.

Train open-vocabulary 3D object detectors using only RGB images and large language models, achieving state-of-the-art performance without expensive LiDAR data.

GroupEXP-DA boosts domain adaptive 3D object detection by using a grouping-exploration strategy to reduce bias in pseudo-label collection and account for multiple factors affecting object perception i…