Jia-Bin Huang

63

Papers

767

Total Citations

Papers (63)

Flow-edge Guided Video Completion

MaskRNN: Instance Level Video Object Segmentation

NeurIPS 2017arXiv

Grounded Text-to-Image Synthesis with Attention Refocusing

Shuffle and Attend: Video Domain Adaptation

Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling

Textured Gaussians for Enhanced 3D Scene Appearance Modeling

In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing

LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields

Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions

MaDCoW: Marginal Distortion Correction for Wide-Angle Photography with Arbitrary Objects

Bridging Diffusion Models and 3D Representations: A 3D Consistent Super-Resolution Framework

Detecting Migrating Birds at Night

Weakly Supervised Object Localization With Progressive Domain Adaptation

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution

DeepMVS: Learning Multi-View Stereopsis

CrDoCo: Pixel-Level Domain Transfer With Cross-Domain Consistency

SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and Baselines

Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Instance-Aware Image Colorization

3D Photography Using Context-Aware Layered Depth Inpainting

Learning to See Through Obstructions

Space-Time Neural Irradiance Fields for Free-Viewpoint Video

Robust Consistent Video Depth Estimation

Boosting View Synthesis With Residual Transfer

Neural Global Shutter: Learn To Restore Video From a Rolling Shutter Camera With Global Reset Feature

Learning Neural Light Fields With Ray-Space Embedding

Shape-Aware Text-Driven Layered Video Editing

DC2: Dual-Camera Defocus Control by Learning To Refocus

Consistent View Synthesis With Pose-Guided Diffusion Models

HyperReel: High-Fidelity 6-DoF Video With Ray-Conditioned Sampling

Progressively Optimized Local Radiance Fields for Robust View Synthesis

Robust Dynamic Radiance Fields

Hierarchical Convolutional Features for Visual Tracking

Unsupervised Representation Learning by Sorting Sequences

Guided Image-to-Image Translation With Bi-Directional Feature Transformation

Hybrid Neural Fusion for Full-Frame Video Stabilization

Dynamic View Synthesis From Dynamic Monocular Video

Neural-PBIR Reconstruction of Shape, Material, and Illumination

Dynamic Mesh-Aware Radiance Fields

Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models

Expressive Text-to-Image Generation with Rich Text

Generative Omnimatte: Learning to Decompose Video into Layers

OmnimatteRF: Robust Omnimatte with 3D Background Modeling

Semantic View Synthesis

DRG: Dual Relation Graph for Human-Object Interaction Detection

NAS-DIP: Learning Deep Image Prior with Neural Architecture Search

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

Temporally Consistent Semantic Video Editing

Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer

Learning Instance-Specific Adaptation for Cross-Domain Segmentation

Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks

ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field

Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation

IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images

VideoGigaGAN: Towards Detail-rich Video Super-Resolution

LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-time Rendering

TextureDreamer: Image-Guided Texture Synthesis Through Geometry-Aware Diffusion

Seeing the World through Your Eyes

On the Content Bias in Fréchet Video Distance

FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis

Single Image Super-Resolution From Transformed Self-Exemplars

A Comparative Study for Single Image Blind Deblurring

Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition