Search Results for author:
Found 15 papers, 6 papers with code
Taming Latent Diffusion Model for Neural Radiance Field Inpainting
These two problems are further reinforced with the use of pixel-distance losses.
Virtual Pets: Animatable Animal Generation in 3D Scenes
Toward unlocking the potential of generative models in immersive 4D experiences, we introduce Virtual Pet, a novel pipeline to model realistic and diverse motions for target animal species within a 3D environment.
DreaMo: Articulated 3D Reconstruction From A Single Casual Video
In this work, we study articulated 3D shape reconstruction from a single and casually captured internet video, where the subject's view coverage is incomplete.
Motion-Conditioned Diffusion Model for Controllable Video Synthesis
In response to this gap, we introduce MCDiff, a conditional diffusion model that generates a video from a starting image frame and a set of strokes, which allow users to specify the intended content and dynamics for synthesis.
InfiniCity: Infinite-Scale City Synthesis
Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which constructs and renders an unconstrainedly large and 3D-grounded environment from random noises.
Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features
Recent studies show that paddings in convolutional neural networks encode absolute position information which can negatively affect the model performance for certain tasks.
InOut: Diverse Image Outpainting via GAN Inversion
Existing image outpainting methods pose the problem as a conditional image-to-image translation task, often generating repetitive structures and textures by replicating the content available in the input image.
InfinityGAN: Towards Infinite-Pixel Image Synthesis
We present a novel framework, InfinityGAN, for arbitrary-sized image generation.
Ranked #2 on
Scene Generation
on OSM
In&Out : Diverse Image Outpainting via GAN Inversion
Existing image outpainting methods pose the problem as a conditional image-to-image translation task, often generating repetitive structures and textures by replicating the content available in the input image.
COCO-GAN: Conditional Coordinate Generative Adversarial Network
The fact that the patch generation process is independent to each other inspires a wide range of new applications: firstly, "Patch-Inspired Image Generation" enables us to generate the entire image based on a single patch.
Point-to-Point Video Generation
We introduce point-to-point video generation that controls the generation process with two control points: the targeted start- and end-frames.
3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization
The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the Li-DAR sensor and stereo camera for improved depth perception.
COCO-GAN: Generation by Parts via Conditional Coordinating
On the computation side, COCO-GAN has a built-in divide-and-conquer paradigm that reduces memory requisition during training and inference, provides high-parallelism, and can generate parts of images on-demand.
Ranked #1 on
Image Generation
on CelebA-HQ 64x64
InstaNAS: Instance-aware Neural Architecture Search
Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy.
Escaping from Collapsing Modes in a Constrained Space
Generative adversarial networks (GANs) often suffer from unpredictable mode-collapsing during training.
Ranked #26 on
Image Generation
on CelebA 64x64
