Kwang Moo Yi

papers

1,917

total citations

papers (28)

VaB-AL: Incorporating Class Imbalance and Difficulty With Variational Bayes for Active Learning

CVPR 2021arXiv

citations

Canonical Capsules: Self-Supervised Capsules in Canonical Pose

NEURIPS 2021arXiv

citations

Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models

CVPR 2024arXiv

citations

Neural Fourier Filter Bank

CVPR 2023arXiv

citations

Pointersect: Neural Rendering With Cloud-Ray Intersection

CVPR 2023arXiv

citations

FaceLit: Neural 3D Relightable Faces

CVPR 2023arXiv

citations

Radiant Foam: Real-Time Differentiable Ray Tracing

ICCV 2025arXiv

citations

ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning

CVPR 2020arXiv

citations

Unsupervised Keypoints from Pretrained Diffusion Models

CVPR 2024arXiv

citations

Accelerating Neural Field Training via Soft Mining

CVPR 2024arXiv

citations

Layered Controllable Video Generation

ECCV 2022arXiv

citations

Volumetric Rendering with Baked Quadrature Fields

ECCV 2024arXiv

citations

BANF: Band-Limited Neural Fields for Levels of Detail Reconstruction

CVPR 2024arXiv

citations

MIST: Multiple Instance Spatial Transformer

CVPR 2021arXiv

citations

TUSK: Task-Agnostic Unsupervised Keypoints

NEURIPS 2022arXiv

citations

BlendFields: Few-Shot Example-Driven Facial Modeling

CVPR 2023arXiv

citations

HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories

CVPR 2025arXiv

citations

StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting

ICCV 2025arXiv

citations

Lagrangian Hashing for Compressed Neural Field Representations

ECCV 2024arXiv

citations

Neural Fields as Distributions: Signal Processing Beyond Euclidean Space

CVPR 2024

citations

Kwang Moo Yi

papers (28)

Kubric: A Scalable Dataset Generator

COTR: Correspondence Transformer for Matching Across Images

NeuMan: Neural Human Radiance Field from a Single Video

DeRF: Decomposed Radiance Fields

Unsupervised Semantic Correspondence Using Stable Diffusion

LOLNerf: Learn From One Look

CoNeRF: Controllable Neural Radiance Fields

ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models

VaB-AL: Incorporating Class Imbalance and Difficulty With Variational Bayes for Active Learning

Canonical Capsules: Self-Supervised Capsules in Canonical Pose

Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models

Neural Fourier Filter Bank

Pointersect: Neural Rendering With Cloud-Ray Intersection

FaceLit: Neural 3D Relightable Faces

Radiant Foam: Real-Time Differentiable Ray Tracing

ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning

Unsupervised Keypoints from Pretrained Diffusion Models

Accelerating Neural Field Training via Soft Mining

Layered Controllable Video Generation

Volumetric Rendering with Baked Quadrature Fields

BANF: Band-Limited Neural Fields for Levels of Detail Reconstruction

MIST: Multiple Instance Spatial Transformer

TUSK: Task-Agnostic Unsupervised Keypoints

BlendFields: Few-Shot Example-Driven Facial Modeling

HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories

StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting

Lagrangian Hashing for Compressed Neural Field Representations

Neural Fields as Distributions: Signal Processing Beyond Euclidean Space

papers (28)

Kubric: A Scalable Dataset Generator

COTR: Correspondence Transformer for Matching Across Images

NeuMan: Neural Human Radiance Field from a Single Video

DeRF: Decomposed Radiance Fields

Unsupervised Semantic Correspondence Using Stable Diffusion

LOLNerf: Learn From One Look

CoNeRF: Controllable Neural Radiance Fields

ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models

VaB-AL: Incorporating Class Imbalance and Difficulty With Variational Bayes for Active Learning

Canonical Capsules: Self-Supervised Capsules in Canonical Pose

Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models

Neural Fourier Filter Bank

Pointersect: Neural Rendering With Cloud-Ray Intersection

FaceLit: Neural 3D Relightable Faces

Radiant Foam: Real-Time Differentiable Ray Tracing

ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning

Unsupervised Keypoints from Pretrained Diffusion Models

Accelerating Neural Field Training via Soft Mining

Layered Controllable Video Generation

Volumetric Rendering with Baked Quadrature Fields

BANF: Band-Limited Neural Fields for Levels of Detail Reconstruction

MIST: Multiple Instance Spatial Transformer

TUSK: Task-Agnostic Unsupervised Keypoints

BlendFields: Few-Shot Example-Driven Facial Modeling

HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories

StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting

Lagrangian Hashing for Compressed Neural Field Representations

Neural Fields as Distributions: Signal Processing Beyond Euclidean Space