Sai-Kit Yeung

28

Papers

26

Total Citations

Papers (28)

360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries

SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting

Color Alignment in Diffusion

TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels

NeurIPS 2025arXiv

Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras

CoralSCOP: Segment any COral Image on this Planet

A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo

A Field Model for Repairing 3D Shapes

GMS: Grid-based Motion Statistics for Fast, Ultra-Robust Feature Correspondence

Radiometric Calibration for Internet Photo Collections

Pointwise Convolutional Neural Networks

Self-Calibrating Polarising Radiometric Calibration

Uncalibrated Photometric Stereo Under Natural Illumination

JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds With Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields

Fill and Transfer: A Simple Physics-Based Approach for Containability Reasoning

An MRF-Poselets Model for Detecting Highly Articulated Humans

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data

ShellNet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells Statistics

Minimal Adversarial Examples for Deep Learning on 3D Point Clouds

Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decoration

Locally Stylized Neural Radiance Fields

360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Tracking

SideInfNet: A Deep Neural Network for Semi-Automatic Semantic Segmentation with Side Information

RFNet-4D: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds

Neural Scene Decoration from a Single Photograph

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

CoralSRT: Revisiting Coral Reef Semantic Segmentation by Feature Rectifying via Self-supervised Guidance

Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates