Probability-Flow Distillation: Exact Wasserstein Gradient Flow for High-Fidelity 3D Generation

• URL: http://arxiv.org/abs/2605.09071v1
• Date: Sat, 09 May 2026 17:27:25 GMT
• Title: Probability-Flow Distillation: Exact Wasserstein Gradient Flow for High-Fidelity 3D Generation
• Abstract summary: We propose a naturally motivated extension termed Probability-Flow Distillation (PFD)<n>PFD corresponds exactly to a Wasserstein gradient flow, thereby principled distribution-matching dynamics.<n>We show that PFD can synthesize 3D assets with fine-grained, high-fidelity details and achieve improved quality compared to existing methods.
• Score: 8.93197829230536
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Score Distillation Sampling (SDS) and its variants have been widely used for text-to-3D generation by distilling 2D image diffusion priors. However, the standard SDS objective is prone to severe mode collapse, frequently yielding over-smoothed and over-saturated results. Although recent advancements, such as Score Distillation via Inversion (SDI), mitigate these artifacts and produce visually sharper models, they ultimately fail to faithfully capture the full target distribution. In this work, we show that the bottleneck limiting the sampling capacity of SDI stems from its reliance on the posterior mean estimator, which is mathematically equivalent to a single-step Euler approximation of the deterministic reverse DDIM trajectory. To address this, we propose a naturally motivated extension termed Probability-Flow Distillation (PFD). We establish that PFD corresponds exactly to a Wasserstein gradient flow, thereby inducing principled distribution-matching dynamics. Finally, we show that PFD can synthesize 3D assets with fine-grained, high-fidelity details and achieve improved quality compared to existing methods.

Related papers

• Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation [51.337622918786074]
  We introduce Tray-Centric Distillation (TraCe), a novel text-to-3D generation framework.<n>TraCe consistently achieves superior quality and fidelity to state-of-the-art techniques.
  arXiv  Detail & Related papers  (2025-11-06T09:21:57Z)
• Score Distillation of Flow Matching Models [67.86066177182046]
  We extend Score identity Distillation (SiD) to pretrained text-to-image flow-matching models.<n>SiD works out of the box across these models, in both data-free and data-aided settings.<n>This provides the first systematic evidence that score distillation applies broadly to text-to-image flow matching models.
  arXiv  Detail & Related papers  (2025-09-29T17:45:48Z)
• Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis [65.77083310980896]
  We propose Adrial Distribution Matching (ADM) to align latent predictions between real and fake score estimators for score distillation.<n>Our proposed method achieves superior one-step performance on SDXL compared to DMD2 while consuming less GPU time.<n>Additional experiments that apply multi-step ADM distillation on SD3-Medium, SD3.5-Large, and CogVideoX set a new benchmark towards efficient image and video synthesis.
  arXiv  Detail & Related papers  (2025-07-24T16:45:05Z)
• SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation [37.329698607074114]
  Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants.<n>Due to the imbalance between self-consistency and cross-consistency, CD-based methods inherently suffer from improper conditional guidance.<n>We present SegmentDreamer, a novel framework designed to fully unleash the potential of consistency models for high-fidelity text-to-3D generation.
  arXiv  Detail & Related papers  (2025-07-07T17:59:05Z)
• Consistent Flow Distillation for Text-to-3D Generation [14.150490171643034]
  Score Distillation Sampling (SDS) has made significant strides in distilling image-generative models for 3D generation.<n>However, its maximum-likelihood-seeking behavior often leads to degraded visual quality and diversity, limiting its effectiveness in 3D applications.<n>We propose Consistent Flow Distillation (CFD), which addresses these limitations.
  arXiv  Detail & Related papers  (2025-01-09T18:56:05Z)
• Diverse Score Distillation [27.790458964072823]
  We propose a score formulation that guides the optimization to follow generation paths defined by random initial seeds.<n>We showcase the applications of our Diverse Score Distillation' (DSD) formulation across tasks such as 2D optimization, text-based 3D inference, and single-view reconstruction.
  arXiv  Detail & Related papers  (2024-12-09T18:59:02Z)
• Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior [87.55592645191122]
  Score distillation sampling (SDS) and its variants have greatly boosted the development of text-to-3D generation, but are vulnerable to geometry collapse and poor textures yet. We propose a novel and effective "Consistent3D" method that explores the ODE deterministic sampling prior for text-to-3D generation. Experimental results show the efficacy of our Consistent3D in generating high-fidelity and diverse 3D objects and large-scale scenes.
  arXiv  Detail & Related papers  (2024-01-17T08:32:07Z)
• SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity [70.32101198891465]
  We show that gradient estimation in score distillation is inherent to high variance. We propose a more general solution to reduce variance for score distillation, termed Stein Score Distillation (SSD) We demonstrate that SteinDreamer achieves faster convergence than existing methods due to more stable gradient updates.
  arXiv  Detail & Related papers  (2023-12-31T23:04:25Z)
• Taming Mode Collapse in Score Distillation for Text-to-3D Generation [70.32101198891465]
  "Janus" artifact is a problem in text-to-3D generation where the generated objects fake each view with multiple front faces. We propose a new update rule for 3D score distillation, dubbed Entropic Score Distillation ( ESD) Although embarrassingly straightforward, our experiments successfully demonstrate that ESD can be an effective treatment for Janus artifacts in score distillation.
  arXiv  Detail & Related papers  (2023-12-31T22:47:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.