# Rethinking Score Distillation as a Bridge Between Image Distributions

arXiv: https://arxiv.org/abs/2406.09417 · HTML: https://mlsanity.com/paper/2406.09417/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 67 of its 77 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 67)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://mlsanity.com/paper/2303.13873/) (2023)
- [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (2023)
- [Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling](https://mlsanity.com/paper/2106.01357/) (2021)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021)
- [Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures](https://mlsanity.com/paper/2211.07600/) (2022)
- [Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors](https://mlsanity.com/paper/2306.17843/) (2023)

## Built on by (most cited first, 30 of 38)

- [Decompositional Neural Scene Reconstruction with Generative Diffusion Prior](https://mlsanity.com/paper/2503.14830/) (2025)
- [Generating Physically Stable and Buildable Brick Structures from Text](https://mlsanity.com/paper/2505.05469/) (2025)
- [Connecting Consistency Distillation to Score Distillation for Text-to-3D Generation](https://mlsanity.com/paper/2407.13584/) (2024)
- [Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization](https://mlsanity.com/paper/2504.02817/) (2025)
- [A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision](https://mlsanity.com/paper/2412.00623/) (2024)
- [RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation](https://mlsanity.com/paper/2502.12640/) (2025)
- [Supercharged One-step Text-to-Image Diffusion Models with Negative Prompts](https://mlsanity.com/paper/2412.02687/) (2024)
- [Let it Snow! Animating 3D Gaussian Scenes with Dynamic Weather Effects via Physics-Guided Score Distillation](https://mlsanity.com/paper/2504.05296/) (2025)
- [Rethinking Score Distilling Sampling for 3D Editing and Generation](https://mlsanity.com/paper/2505.01888/) (2025)
- [Geometry-Aware Diffusion Models for Multiview Scene Inpainting](https://mlsanity.com/paper/2502.13335/) (2025)
- [Illusion3D: 3D Multiview Illusion with 2D Diffusion Priors](https://mlsanity.com/paper/2412.09625/) (2024)
- [Balanced Image Stylization with Style Matching Score](https://mlsanity.com/paper/2503.07601/) (2025)
- [Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D Generation](https://mlsanity.com/paper/2505.05505/) (2025)
- [Animus3D: Text-driven 3D Animation via Motion Score Distillation](https://mlsanity.com/paper/2512.12534/) (2025)
- [RewardSDS: Aligning Score Distillation via Reward-Weighted Sampling](https://mlsanity.com/paper/2503.09601/) (2025)
- [Delta Rectified Flow Sampling for Text-to-Image Editing](https://mlsanity.com/paper/2509.05342/) (2025)
- [Coupled Diffusion Sampling for Training-Free Multi-View Image Editing](https://mlsanity.com/paper/2510.14981/) (2025)
- [GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction](https://mlsanity.com/paper/2512.25073/) (2025)
- [Guidance Free Image Editing via Explicit Conditioning](https://mlsanity.com/paper/2503.17593/) (2025)
- [Walking the Schr"odinger Bridge: A Direct Trajectory for Text-to-3D Generation](https://mlsanity.com/paper/2511.05609/) (2025)
- [Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching](https://mlsanity.com/paper/2602.12280/) (2026)
- [MobileWan: Closing the Quality Gap for Mobile Video Diffusion](https://mlsanity.com/paper/2607.06173/) (2026)
- [Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling](https://mlsanity.com/paper/2510.23605/) (2025)
- [AnchorDS: Anchoring Dynamic Sources for Semantically Consistent Text-to-3D Generation](https://mlsanity.com/paper/2511.11692/) (2025)
- [Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference](https://mlsanity.com/paper/2603.01594/) (2026)
- [Variance Reduction for Expectations with Diffusion Teachers](https://mlsanity.com/paper/2605.21489/) (2026)
- [LUSD: Localized Update Score Distillation for Text-Guided Image Editing](https://mlsanity.com/paper/2503.11054/) (2025)
- [SV-GS: Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splatting](https://mlsanity.com/paper/2601.00285/) (2026)
- [Ani3DHuman: Photorealistic 3D Human Animation with Self-guided Stochastic Sampling](https://mlsanity.com/paper/2602.19089/) (2026)
- [From Competition to Coopetition: Coopetitive Training-Free Image Editing Based on Text Guidance](https://mlsanity.com/paper/2604.15948/) (2026)

## Abstract (arXiv)

Score distillation sampling (SDS) has proven to be an important tool, enabling the use of large-scale diffusion priors for tasks operating in data-poor domains. Unfortunately, SDS has a number of characteristic artifacts that limit its usefulness in general-purpose applications. In this paper, we make progress toward understanding the behavior of SDS and its variants by viewing them as solving an optimal-cost transport path from a source distribution to a target distribution. Under this new interpretation, these methods seek to transport corrupted images (source) to the natural image distribution (target). We argue that current methods' characteristic artifacts are caused by (1) linear approximation of the optimal path and (2) poor estimates of the source distribution. We show that calibrating the text conditioning of the source distribution can produce high-quality generation and translation results with little extra overhead. Our method can be easily applied across many domains, matching or beating the performance of specialized methods. We demonstrate its utility in text-to-2D, text-based NeRF optimization, translating paintings to real images, optical illusion generation, and 3D sketch-to-real. We compare our method to existing approaches for score distillation sampling and show that it can produce high-frequency details with realistic colors.