Stories by lnyan

Diffusion Models for Video Prediction and Infilling

Gram-HD: 3D-Consistent Image Generation with Generative Radiance Manifolds

Variable Bitrate Neural Fields

VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids

Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesis

CogView2: A 24 billion parameter text-to-image generation model

CogView2: Faster & Better Text-to-Image Generation via Hierarchical Transformer

OCaml-torch: OCaml bindings for PyTorch

Voronoi Diagrams on the GPU (2016)

ReCo: Retrieve and Co-segment for Zero-shot Transfer

Object Scene Representation Transformer

RigNeRF: Fully Controllable Neural 3D Portraits

Peripheral Vision Transformer

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

Direct Voxel Grid Optimization

How Much Is Enough? A Study on Diffusion Times in Score-Based Generative Models

ARF: Artistic Radiance Fields

SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views

Meta Optimal Transport

Josephus Problem

25
26
27
28
29
30
31
32
33
34