research
∙
07/27/2023
Online Clustered Codebook
Vector Quantisation (VQ) is experiencing a comeback in machine learning,...
share
research
∙
07/06/2023
IPO-LDM: Depth-aided 360-degree Indoor RGB Panorama Outpainting via Latent Diffusion Model
Generating complete 360-degree panoramas from narrow field of view image...
research
∙
06/01/2023
Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation
Text-conditional diffusion models are able to generate high-fidelity ima...
research
∙
04/24/2023
Explicit Correspondence Matching for Generalizable Neural Radiance Fields
We present a new generalizable NeRF method that is able to directly gene...
research
∙
02/12/2023
Vector Quantized Wasserstein Auto-Encoder
Learning deep discrete latent presentations offers a promise of better s...
research
∙
11/27/2022
Unified Discrete Diffusion for Simultaneous Vision-Language Generation
The recently developed discrete diffusion models perform extraordinarily...
research
∙
09/19/2022
MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation
Although two-stage Vector Quantized (VQ) generative models allow for syn...
research
∙
07/20/2022
Object-Compositional Neural Implicit Surfaces
The neural implicit representation has shown its effectiveness in novel ...
research
∙
04/05/2022
High-Quality Pluralistic Image Completion via Code Shared VQGAN
PICNet pioneered the generation of multiple and diverse results for imag...
research
∙
03/21/2022
Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields
Image translation and manipulation have gain increasing attention along ...
research
∙
02/23/2022
Synthesizing Photorealistic Images with Deep Generative Learning
The goal of this thesis is to present my research contributions towards ...
research
∙
04/12/2021
Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition
Existing scene understanding systems mainly focus on recognizing the vis...
research
∙
04/02/2021
The Spatially-Correlative Loss for Various Image Translation Tasks
We propose a novel spatially-correlative loss that is simple, efficient ...
research
∙
04/02/2021
TFill: Image Completion via a Transformer-Based Architecture
Bridging distant context interactions is important for high quality imag...
research
∙
03/11/2019
Pluralistic Image Completion
Most image completion methods produce only one result for each masked in...
research
∙
08/04/2018
