Ceyuan Yang

28

Papers

401

Total Citations

Papers (28)

GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

Learning Where to Focus for Efficient Video Object Detection

Long Context Tuning for Video Generation

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

Keyframe-Guided Creative Video Inpainting

BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation

Adapting Object Detectors via Selective Cross-Domain Alignment

Temporal Pyramid Network for Action Recognition

Instance Localization for Self-Supervised Detection Pretraining

Generative Hierarchical Features From Synthesizing Images

3D-Aware Image Synthesis via Learning Structural and Textural Representations

Improving GAN Equilibrium by Raising Spatial Awareness

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis

GLeaD: Improving GANs With a Generator-Leading Task

LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis

One-Shot Generative Domain Adaptation

Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation

SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models

Edicho: Consistent Image Editing in the Wild

Towards Text-guided 3D Scene Composition

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

SMaRt: Improving GANs with Score Matching Regularity

Data-Efficient Instance Generation from Instance Discrimination

Improving GANs with A Dynamic Discriminator

Learning Modulated Transformation in GANs

Revisiting the Evaluation of Image Synthesis with GANs