RealmDreamer generates high-quality 3D scenes from text prompts by leveraging pretrained 2D inpainting and depth diffusion models to produce scenes with parallax, detailed appearance, and accurate geometry.
Carve3D, an improved Reinforcement Learning Finetuning (RLFT) algorithm coupled with a novel Multi-view Reconstruction Consistency (MRC) metric, enhances the consistency of multi-view diffusion models without sacrificing their prompt alignment, texture details, or diversity.
DreamView enables customizable and consistent text-to-3D generation by adaptively injecting overall and view-specific text guidance into a diffusion model.
GSGEN, a novel method that adopts Gaussian Splatting to generate high-quality 3D objects with accurate geometry and delicate details by exploiting the explicit nature of Gaussian Splatting and incorporating direct 3D priors.
Stein Score Distillation (SSD) incorporates flexible control variates derived from Stein's identity to effectively reduce the variance in the gradient estimation of score distillation, leading to improved text-to-3D generation quality and faster convergence.
Existing score distillation-based text-to-3D generation frameworks degenerate to maximal likelihood seeking on each view independently, leading to the mode collapse problem and manifesting as the Janus artifact. To address this issue, the authors propose Entropic Score Distillation (ESD), which regularizes the score distillation process by entropy maximization of the rendered image distribution, thereby enhancing the diversity of views in generated 3D assets and alleviating the Janus problem.