Chen Change Loy

152

Papers

1,223

Total Citations

Papers (152)

Knowledge Distillation Meets Self-Supervision

Local Similarity-Aware Deep Feature Embedding

NeurIPS 2016arXiv

VideoBooth: Diffusion-based Video Generation with Image Prompts

OMG-Seg: Is One Model Good Enough For All Segmentation?

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation

FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation

Digital Life Project: Autonomous 3D Characters with Social Intelligence

Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment

Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

Towards Language-Driven Video Inpainting via Multimodal Large Language Models

MVIP-NeRF: Multi-view 3D Inpainting on NeRF Scenes via Diffusion Prior

CLIM: Contrastive Language-Image Mosaic for Region Representation

F-LMM: Grounding Frozen Large Multimodal Models

Explore In-Context Segmentation via Latent Diffusion Models

Kalman-Inspired Feature Propagation for Video Face Super-Resolution

Adaptive Window Pruning for Efficient Local Motion Deblurring

3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement

DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting

GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects

Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade

Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform

Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning

Pose-Robust Face Recognition via Deep Residual Equivariant Mapping

Optimizing Video Object Detection via a Scale-Time Lattice

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation

Learning a Unified Classifier Incrementally via Rebalancing

Deep Network Interpolation for Continuous Imagery Effect Transition

Self-Supervised Learning via Conditional Motion Propagation

Learning to Cluster Faces on an Affinity Graph

Region Proposal by Guided Anchoring

Dense Intrinsic Appearance Flow for Human Pose Transfer

Deep Flow-Guided Video Inpainting

Hybrid Task Cascade for Instance Segmentation

TransGaGa: Geometry-Aware Unsupervised Image-To-Image Translation

Self-Supervised Scene De-Occlusion

DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection

Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

Online Deep Clustering for Unsupervised Representation Learning

TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting

Inter-Region Affinity Distillation for Road Marking Segmentation

Learning to Cluster Faces via Confidence and Connectivity Estimation

EcoNAS: Finding Proxies for Economical Neural Architecture Search

Prime Sample Attention in Object Detection

Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network

Audio-Driven Emotional Video Portraits

BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond

Positional Encoding As Spatial Inductive Bias in GANs

Seesaw Loss for Long-Tailed Instance Segmentation

Pareidolia Face Reenactment

Deep Animation Video Interpolation in the Wild

Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation

Robust Reference-Based Super-Resolution via C2-Matching

GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution

Unsupervised 3D Shape Completion Through GAN Inversion

Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer

Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation

Bailando: 3D Dance Generation by Actor-Critic GPT With Choreographic Memory

BasicVSR++: Improving Video Super-Resolution With Enhanced Propagation and Alignment

Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation

Conditional Prompt Learning for Vision-Language Models

Investigating Tradeoffs in Real-World Video Super-Resolution

TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing

Unsupervised Image-to-Image Translation With Generative Prior

Aligning Bag of Regions for Open-Vocabulary Object Detection

Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior

CelebV-Text: A Large-Scale Facial Text-Video Dataset

Siamese DETR

Correlational Image Modeling for Self-Supervised Visual Pre-Training

Panoptic Video Scene Graph Generation

Learning Generative Structure Prior for Blind Text Image Super-Resolution

Generating Aligned Pseudo-Supervision From Non-Aligned Data for Image Restoration in Under-Display Camera

Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion

Compression Artifacts Reduction by a Deep Convolutional Network

Be Your Own Prada: Fashion Synthesis With Structural Coherence

Learning to Disambiguate by Asking Discriminative Questions

Learning Lightweight Lane Detection CNNs by Self Attention Distillation

Robust Multi-Modality Multi-Object Tracking

CARAFE: Content-Aware ReAssembly of FEatures

Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild

3D Human Texture Estimation From a Single Image With Transformers

FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation

ReconfigISP: Reconfigurable Camera Image Processing Pipeline

Talk-To-Edit: Fine-Grained Facial Editing via Dialog

Focal Frequency Loss for Image Reconstruction and Synthesis

Deep Geometrized Cartoon Line Inbetweening

MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions

Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translation

DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-Centric Rendering

SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis

ProPainter: Improving Propagation and Transformer for Video Inpainting

Iterative Prompt Learning for Unsupervised Backlit Image Enhancement

DeformToon3D: Deformable Neural Radiance Fields for 3D Toonification

Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation

Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation

StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces

Text2Performer: Text-Driven Human Video Generation

StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation

TSIT: A Simple and Versatile Framework for Image-to-Image Translation

Side-Aware Boundary Localization for More Precise Object Detection

RGB-D Salient Object Detection with Cross-Modality Modulation and Selection

MessyTable: Instance Association in Multiple Camera Views

LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation

Monocular 3D Object Reconstruction with GAN Inversion

LEDNet: Joint Low-Light Enhancement and Deblurring in the Dark

HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling

CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis

Open-Vocabulary DETR with Conditional Matching

StyleLight: HDR Panorama Generation for Lighting Estimation and Editing

StyleGAN-Human: A Data-Centric Odyssey of Human Generation

Transformer with Implicit Edges for Particle-Based Physics Simulation

Extract Free Dense Labels from CLIP

Dense Siamese Network for Dense Unsupervised Learning

Mind the Gap in Distilling StyleGANs

Towards Multi-Layered 3D Garments Animation

Arbitrary-steps Image Super-resolution via Diffusion Inversion

MatAnyone: Stable Video Matting with Consistent Memory Propagation

SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention

EdgeTAM: On-Device Track Anything Model

SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer

Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpainting

Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis

PaintHuman: Towards High-Fidelity Text-to-3D Human Texturing via Denoised Score Distillation

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution

When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation

Learning Inclusion Matching for Animation Paint Bucket Colorization

A Large-Scale Car Dataset for Fine-Grained Categorization and Verification

Deeply Learned Attributes for Crowded Scene Understanding

Face Alignment by Coarse-to-Fine Shape Searching

Unsupervised Learning of Discriminative Attributes and Visual Representations

Learning Deep Representation for Imbalanced Classification

PolyNet: A Pursuit of Structural Diversity in Very Deep Networks

Discover and Learn New Objects From Documentaries

Non-Local Recurrent Network for Image Restoration

Cross-Scale Internal Graph Neural Network for Image Super-Resolution

K-Net: Towards Unified Image Segmentation

A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis

Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

Unsupervised Object-Level Representation Learning from Scene Images

Flare7K: A Phenomenological Nighttime Flare Removal Dataset

AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies

Deep Fourier Up-Sampling

Towards Robust Blind Face Restoration with Codebook Lookup Transformer

RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars

SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting

Rubik's Cube: High-Order Channel Interactions with a Hierarchical Receptive Field

PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance

Explore In-Context Learning for 3D Point Cloud Understanding