Stories by lnyan

MonoSDF: Exploring Monocular Cues for Neural Implicit Surface Reconstruction

IDE-3D: Interactive Disentangled Editing for 3D-Aware Portrait Synthesis

Samurai: Shape and Material from Unconstrained Real-World Image Collections

"Finish the cat drawing" via DALL-E-2’s inpainting function

Text2Human: Text-Driven Controllable Human Image Generation

Few-Shot Diffusion Models

Decomposing NeRF for Editing via Feature Field Distillation

D2NeRF: Decoupling of Dynamic and Static Objects from a Monocular Video

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

TiNeuVox: Fast Dynamic Radiance Fields with Time-Aware Neural Voxels

Neural Volumetric Object Selection

Neural Shape Mating: Object Assembly with Adversarial Shape Priors

CogVideo: Large-Scale Pretraining for Text-to-Video Generation via Transformers

GIT: A Generative Image-to-Text Transformer for Vision and Language

3DILG: Irregular Latent Grids for 3D Generative Modeling

Video2StyleGAN: Disentangling Local and Global Variations in a Video

Cross-Domain Style Mixing for Face Cartoonization

Learning the Beauty in Songs: Neural Singing Voice Beautifier

Ray-optics: a web app to simulate the reflection and refraction of light

Evaluating Multimodal Interactive Agents

28
29
30
31
32
33
34
35
36
37