Image-to-3D

Zero123++ can generate high-quality, 3D-consistent multi-view images from a single input image using an image-conditioned diffusion model. It fixes common problems like blurry textures and misaligned shapes, and includes a ControlNet for better control over the image creation process.

Wonder3D is able to convert a single image into a high-fidelity 3D model, complete with textured meshes and color. The entire process takes only 2 to 3 minutes.

DreamGaussian can generate high-quality textured meshes from a single-view image in just 2 minutes. It uses a 3D Gaussian Splatting model for fast mesh extraction and texture refinement.

PlankAssembly can turn 2D line drawings from three views into 3D CAD models. It effectively handles noisy or incomplete inputs and improves accuracy using shape programs.

Similar like ControlNet scribble for images, SketchMetaFace brings sketch guidance to the 3D realm and makes it possible to turn a sketch into a 3D face model. Pretty excited about progress like this, as this will bring controllability to 3D generations and make generating 3D content way more accessible.

PAniC-3D can reconstruct 3D character heads from single-view anime portraits. It uses a line-filling model and a volumetric radiance field, achieving better results than previous methods and setting a new standard for stylized reconstruction.

Make-It-3D can create high-quality 3D content from a single image by estimating 3D shapes and adding textures. It uses a two-step process with a trained 2D diffusion model, allowing for text-to-3D creation and detailed texture editing.

SceneDreamer can generate endless 3D scenes from 2D image collections. It creates photorealistic images with clear depth and allows for free camera movement in the environments.

EVA3D can generate high-quality 3D human models from 2D image collections. It uses a method called compositional NeRF for detailed shapes and textures, and it improves learning with pose-guided sampling.