CVAIGTMMSep 18, 2024

Vista3D: Unravel the 3D Darkside of a Single Image

arXiv:2409.12193v13 citationsh-index: 11Has Code
Originality Highly original
AI Analysis

This addresses the challenge of reconstructing hidden 3D dimensions from limited 2D views for applications in computer vision and graphics, representing a novel method for a known bottleneck.

The paper tackles the problem of generating 3D objects from a single image, achieving swift and consistent 3D generation within 5 minutes by using a two-phase approach with Gaussian Splatting and SDF optimization.

We embark on the age-old quest: unveiling the hidden dimensions of objects from mere glimpses of their visible parts. To address this, we present Vista3D, a framework that realizes swift and consistent 3D generation within a mere 5 minutes. At the heart of Vista3D lies a two-phase approach: the coarse phase and the fine phase. In the coarse phase, we rapidly generate initial geometry with Gaussian Splatting from a single image. In the fine phase, we extract a Signed Distance Function (SDF) directly from learned Gaussian Splatting, optimizing it with a differentiable isosurface representation. Furthermore, it elevates the quality of generation by using a disentangled representation with two independent implicit functions to capture both visible and obscured aspects of objects. Additionally, it harmonizes gradients from 2D diffusion prior with 3D-aware diffusion priors by angular diffusion prior composition. Through extensive evaluation, we demonstrate that Vista3D effectively sustains a balance between the consistency and diversity of the generated 3D objects. Demos and code will be available at https://github.com/florinshen/Vista3D.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes