REVIEW 4 cited by
Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Text-to-3D generation has shown rapid progress in recent days with the advent of score distillation, a methodology of using pretrained text-to-2D diffusion models to optimize neural radiance field (NeRF) in the zero-shot setting. However, the lack of 3D awareness in the 2D diffusion models destabilizes score distillation-based methods from reconstructing a plausible 3D scene. To address this issue, we propose 3DFuse, a novel framework that incorporates 3D awareness into pretrained 2D diffusion models, enhancing the robustness and 3D consistency of score distillation-based methods. We realize this by first constructing a coarse 3D structure of a given text prompt and then utilizing projected, view-specific depth map as a condition for the diffusion model. Additionally, we introduce a training strategy that enables the 2D diffusion model learns to handle the errors and sparsity within the coarse 3D structure for robust generation, as well as a method for ensuring semantic consistency throughout all viewpoints of the scene. Our framework surpasses the limitations of prior arts, and has significant implications for 3D consistent generation of 2D diffusion models.
Forward citations
Cited by 4 Pith papers
-
CLEAR: Conflict-aware Learning via Evidence-guided Adaptive Routing for Unified Sparse-View 3D Gaussian Super-Resolution
CLEAR performs single-stage joint training of a 3D Gaussian scene under low- and high-resolution supervision, using conflict-aware gradient correction and evidence-guided detail routing to reach state-of-the-art spars...
-
Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation
Updating the LoRA score model one step ahead of the 3D model and keeping only the first-order correction term yields L2-VSD, a stable and higher-quality variant of VSD for text-to-3D generation.
-
WAVE: Warp-Based View Guidance for Consistent Novel View Synthesis Using a Single Image
A training-free method, WAVE, improves multi-view consistency in single-image novel view synthesis by using 3D-warped views to guide diffusion attention and initial noise.
-
Few-step Flow for 3D Generation via Marginal-Data Transport Distillation
MDT-dist distills a pretrained 3D flow model into a 1-2 step generator using velocity matching plus velocity distillation, cutting TRELLIS inference from 6.1s to 0.68s while approximately preserving generation quality.
Discussion (0). Sign in to comment.