pengHTYX
Follow
Stars
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
A set of tools to visualize and interact with sequences of 3D data.
A Modular Framework for 3D Gaussian Splatting and Beyond
Transparent Image Layer Diffusion using Latent Transparency
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
[CVPR 2024 Highlight] The official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"
[CVPR 2024 Highlight] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering
Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"
[CVPR 2024 Highlight] The official repo for “GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis”
An open-source impl. of Large Reconstruction Models
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
"FreeU: Free Lunch in Diffusion U-Net" for Huggingface Diffusers
FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)
[ICLR 2024] Github Repo for "HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion"
This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models
A Unified Framework for Surface Reconstruction
[ICCV2023] Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement
Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
recurrence of the paper "Consistent View Synthesis with Pose-Guided Diffusion Models"
Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
A collection of resources on digital human including clothed people digitalization, virtual try-on, and other related directions.