Dejia Xu

Orcid: 0000-0001-8474-3095

According to our database1, Dejia Xu authored at least 53 papers between 2020 and 2025.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
TiP4GEN: Text to Immersive Panorama 4D Scene Generation.
CoRR, August, 2025

HardTests: Synthesizing High-Quality Test Cases for LLM Coding.
CoRR, May, 2025

Can Test-Time Scaling Improve World Foundation Model?
CoRR, March, 2025

Copy or Not? Reference-Based Face Image Restoration with Fine Details.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

RagMe: Retrieval Augmented Video Generation for Enhanced Motion Realism.
Proceedings of the 2025 International Conference on Multimedia Retrieval, 2025

4K4DGen: Panoramic 4D Generation at 4K Resolution.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Atlas Gaussians Diffusion for 3D Generation.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

YOLO-KED: A Novel Framework for Rotated Object Detection in Complex Environments.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024
AGG: Amortized Generative 3D Gaussians for Single Image to 3D.
Trans. Mach. Learn. Res., 2024

Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention.
CoRR, 2024

Atlas Gaussians Diffusion for 3D Generation with Infinite Number of Points.
CoRR, 2024

4K4DGen: Panoramic 4D Generation at 4K Resolution.
CoRR, 2024

CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation.
CoRR, 2024

LLMGeo: Benchmarking Large Language Models on Image Geolocation In-the-wild.
CoRR, 2024

Comp4D: LLM-Guided Compositional 4D Scene Generation.
CoRR, 2024

VASE: Object-Centric Appearance and Shape Manipulation of Real Videos.
CoRR, 2024

Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting.
Proceedings of the Computer Vision - ECCV 2024, 2024

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Taming Mode Collapse in Score Distillation for Text-to-3D Generation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

OpenBias: Open-Set Bias Detection in Text-to-Image Generative Models.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

NeRF as Pretraining at Scale: Generalizable 3D-Aware Semantic Representation Learning from View Prediction.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
Background Scene Recovery From an Image Looking Through Colored Glass.
IEEE Trans. Multim., 2023

4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency.
CoRR, 2023

Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else.
CoRR, 2023

Drag View: Generalizable Novel View Synthesis with Unposed Imagery.
CoRR, 2023

Reference-based Painterly Inpainting via Diffusion: Crossing the Wild Reference Domain Gap.
CoRR, 2023

POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference.
CoRR, 2023

PAIR-Diffusion: Object-Level Image Editing with Structure-and-Appearance Paired Diffusion Models.
CoRR, 2023

CLE Diffusion: Controllable Light Enhancement Diffusion Model.
Proceedings of the 31st ACM International Conference on Multimedia, 2023

Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation.
Proceedings of the International Conference on Machine Learning, 2023

NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing.
Proceedings of the IEEE/ACM International Conference on Computer Aided Design, 2023

NeuralLift-360: Lifting an in-the-Wild 2D Photo to A 3D Object with 360° Views.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Signal Processing for Implicit Neural Representations.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

ReCoRo: Region-Controllable Robust Light Enhancement with User-Specified Imprecise Masks.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Cloud2Sketch: Augmenting Clouds with Imaginary Sketches.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image.
Proceedings of the Computer Vision - ECCV 2022, 2022

Unified Implicit Neural Stylization.
Proceedings of the Computer Vision - ECCV 2022, 2022

2021
Benchmarking Low-Light Image Enhancement and Beyond.
Int. J. Comput. Vis., 2021

Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study.
Proceedings of the 9th International Conference on Learning Representations, 2021

2020



Moiré Pattern Removal via Attentive Fractal Network.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020


Towards Scale-Free Rain Streak Removal via Self-Supervised Fractal Band Learning.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020


  Loading...