Harnessing the Power of Training-Free Techniques in Text-to-2D Generation for Text-to-3D Generation via Score Distillation Sampling
Recent studies show that simple training-free techniques can dramatically improve the quality of text-to-2D generation outputs, e.g. Classifier-Free Guidance (CFG) or FreeU. However, these training-free techniques have been underexplored in the lens of Score Distillation Sampling (SDS), which is a popular and effective technique to leverage the power of pretrained text-to-2D diffusion models for various tasks. In this paper, we aim to shed light on the effect such training-free techniques have on SDS, via a particular application of text-to-3D generation via 2D lifting. We present our findings, which show that varying the scales of CFG presents a trade-off between object size and surface smoothness, while varying the scales of FreeU presents a trade-off between texture details and geometric errors. Based on these findings, we provide insights into how we can effectively harness training-free techniques for SDS, via a strategic scaling of such techniques in a dynamic manner with respect to the timestep or optimization iteration step. We show that using our proposed scheme strikes a favorable balance between texture details and surface smoothness in text-to-3D generations, while preserving the size of the output and mitigating the occurrence of geometric defects.
Code (0)
등록된 구현이 없습니다.
Tasks
3D GenerationText to 3DMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Harnessing Machine Learning for Single-Shot Measurement of Free Electron Laser Pulse Power
Electron beam accelerators are essential in many scientific and technological fields. Their operation relies heavily on the stability and precision of the electron beam. Traditional diagnostic techniques encounter diffic…
DiagnosticGenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings
Training-free embedding methods directly leverage pretrained large language models (LLMs) to embed text, bypassing the costly and complex procedure of contrastive learning. Previous training-free embedding methods have m…
Contrastive LearningMTEB BenchmarkRerankingSentence+6Label-Free Topic-Focused Summarization Using Query Augmentation
In today's data and information-rich world, summarization techniques are essential in harnessing vast text to extract key information and enhance decision-making and efficiency. In particular, topic-focused summarization…
Decision MakingEvolution of IVR building techniques: from code writing to AI-powered automation
Interactive Voice Response (IVR) systems have undergone significant transformation in recent years, moving from traditional code-based development to more user-friendly approaches leveraging widgets and, most recently, h…
Reinforcement Learning via Replica Stacking of Quantum Measurements for the Training of Quantum Boltzmann Machines
Recent theoretical and experimental results suggest the possibility of using current and near-future quantum hardware in challenging sampling tasks. In this paper, we introduce free-energy-based reinforcement learning (F…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)