Search Results for author:
Found 27 papers, 17 papers with code
ZeroKey: Point-Level Reasoning and Zero-Shot 3D Keypoint Detection from Large Language Models
Experimental evaluations demonstrate that our approach achieves competitive performance on standard benchmarks compared to supervised methods, despite not requiring any 3D keypoint annotations during training.
3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes
Our results highlight the potential of 3D Convex Splatting to become the new standard for high-quality scene reconstruction and novel view synthesis.
GST: Precise 3D Human Body from a Single Image with Gaussian Splatting Transformers
Our key observation is that the vertices of standardized human meshes (such as SMPL) can provide an adequate density and approximate initial position for Gaussians.
TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks
Neural radiance fields (NeRFs) generally require many images with accurate poses for accurate novel view synthesis, which does not reflect realistic setups where views can be sparse and poses can be noisy.
Medical SAM 2: Segment medical images as video via Segment Anything Model 2
Medical image segmentation plays a pivotal role in clinical diagnostics and treatment planning, yet existing models often face challenges in generalization and in handling both 2D and 3D data uniformly.
Towards AI-Powered Video Assistant Referee System (VARS) for Association Football
VARS sets a new state-of-the-art on the SoccerNet-MVFoul dataset, a multi-view video dataset of football fouls.
Hybrid Structure-from-Motion and Camera Relocalization for Enhanced Egocentric Localization
We built our pipeline EgoLoc-v1, mainly inspired by EgoLoc.
X-Diffusion: Generating Detailed 3D MRI Volumes From a Single Image Using Cross-Sectional Diffusion Models
In this work, we present X-Diffusion, a cross-sectional diffusion model tailored for Magnetic Resonance Imaging (MRI) data.
GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering
With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks while requiring less than half the memory storage of Gaussian Splatting and increasing the rendering speed by up to 39%.
GES : Generalized Exponential Splatting for Efficient Radiance Field Rendering
With the aid of a frequency-modulated loss GES achieves competitive performance in novel-view synthesis benchmarks while requiring less than half the memory storage of Gaussian Splatting and increasing the rendering speed by up to 39%.
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors.
Mindstorms in Natural Language-Based Societies of Mind
What should be the social structure of an NLSOM?
VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views
The Video Assistant Referee (VAR) has revolutionized association football, enabling referees to review incidents on the pitch, make informed decisions, and ensure fairness.
MVTN: Learning Multi-View Transformations for 3D Understanding
Multi-view projection techniques have shown themselves to be highly effective in achieving top-performing results in the recognition of 3D shapes.
SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Images
SuRFNet employs partial SRFs from few/one images and a specialized SRF loss to learn to generate high-quality sparse voxel radiance fields that can be rendered from novel views.
EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries
Yet, we point out that the low number of camera poses caused by camera re-localization from previous VQ3D methods severally hinders their overall success rate.
Estimating more camera poses for ego-centric videos is essential for VQ3D
Visual queries 3D localization (VQ3D) is a task in the Ego4D Episodic Memory Benchmark.
Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding
Pretrained on a large number of widely available images, significant gains of PViT are observed in the tasks of 3D point cloud classification, part segmentation, and semantic segmentation on ScanObjectNN, ShapeNetPart, and S3DIS, respectively.
Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding
To this end, we introduce the concept of the multi-view point cloud (Voint cloud), representing each 3D point as a set of features extracted from several view-points.
MVTN: Multi-View Transformation Network for 3D Shape Recognition
MVTN exhibits clear performance gains in the tasks of 3D shape classification and 3D shape retrieval without the need for extra training supervision.
Ranked #1 on
3D Object Retrieval
on ModelNet40
AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds
Our proposed attack increases the attack success rate by up to 40% for those transferred to unseen networks (transferability), while maintaining a high success rate on the attacked network.
Expected Tight Bounds for Robust Deep Neural Network Training
al. that bounded input intervals can be inexpensively propagated from layer to layer through deep networks.
Expected Tight Bounds for Robust Training
In this paper, we closely examine the bounds of a block of layers composed in the form of Affine-ReLU-Affine.
IAN: Combining Generative Adversarial Networks for Imaginative Face Generation
Generative Adversarial Networks (GANs) have gained momentum for their ability to model image distributions.
Towards Analyzing Semantic Robustness of Deep Neural Networks
Despite the impressive performance of Deep Neural Networks (DNNs) on various vision tasks, they still exhibit erroneous high sensitivity toward semantic primitives (e. g. object pose).
SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications
In contrast, we present a general framework for adversarial attacks on trained agents, which covers semantic perturbations to the environment of the agent performing the task as well as pixel-level attacks.
Learning Rotation for Kernel Correlation Filter
Kernel Correlation Filters have shown a very promising scheme for visual tracking in terms of speed and accuracy on several benchmarks.
