Highlights
- Pro
Stars
Official code release for ConceptGraphs
[RA-L2025] ActiveGS: Active Scene Reconstruction Using Gaussian Splatting
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.
GraspSplats: Efficient Manipulation with 3D Feature Splatting
A framework for high-quality material transfer that allows users to adjust the degree of material application.
MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion
RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
[ICCV2025]Generate one 2K image on single 3090 GPU!
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
Fast and memory-efficient exact attention
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
An official implementation of PRM, a feed-forward framework for high-quality 3D mesh generation from a single image.
Official PyTorch implementation of the CVPR 2024 Highlight Paper "Real-time 3D-aware Portrait Video Relighting"
Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA
Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]
UV-free Texture Diffusion (UV3-TeD) is a denoising diffusion probabilistic model constrained to operate on the surface of 3D objects and capable of generating textures as coloured point-clouds.
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
[SIGGRAPH2024] DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
Interactive Text-to-Texture Synthesis via Unified Depth-aware Inpainting.
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
STAR: Scale-wise Text-to-image generation via Auto-Regressive representations