English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Text-to-3D generation has recently garnered significant attention, fueled by2D diffusion models trained on billions of image-text pairs. Existing methodsprimarily rely on score distillation to leverage the 2D diffusion priors tosupervise the generation of 3D models, e.g., NeRF. However, score distillationis prone to suffer the view inconsistency problem, and implicit NeRF modelingcan also lead to an arbitrary shape, thus leading to less realistic anduncontrollable 3D generation. In this work, we propose a flexible framework ofPoints-to-3D to bridge the gap between sparse yet freely available 3D pointsand realistic shape-controllable 3D generation by distilling the knowledge fromboth 2D and 3D diffusion models. The core idea of Points-to-3D is to introducecontrollable sparse 3D points to guide the text-to-3D generation. Specifically,we use the sparse point cloud generated from the 3D diffusion model, Point-E,as the geometric prior, conditioned on a single reference image. To betterutilize the sparse 3D points, we propose an efficient point cloud guidance lossto adaptively drive the NeRF's geometry to align with the shape of the sparse3D points. In addition to controlling the geometry, we propose to optimize theNeRF for a more view-consistent appearance. To be specific, we perform scoredistillation to the publicly available 2D image diffusion model ControlNet,conditioned on text as well as depth map of the learned compact geometry.Qualitative and quantitative comparisons demonstrate that Points-to-3D improvesview consistency and achieves good shape controllability for text-to-3Dgeneration. Points-to-3D provides users with a new way to improve and controltext-to-3D generation.

Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation