# Score Distillation via Reparametrized DDIM

arXiv: https://arxiv.org/abs/2405.15891 · HTML: https://mlsanity.com/paper/2405.15891/

## Key facts

- Cited by 41 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 42 of its 49 references that are in the map.
- First posted on arXiv 24 May 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 42)

- [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)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [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)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (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)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://mlsanity.com/paper/2303.13873/) (2023)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior](https://mlsanity.com/paper/2303.14184/) (2023)
- [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://mlsanity.com/paper/2305.08891/) (2023)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching](https://mlsanity.com/paper/2311.11284/) (2023)
- [Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models](https://mlsanity.com/paper/2305.16807/) (2023)
- [Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond](https://mlsanity.com/paper/2304.04968/) (2023)

## Built on by (most cited first, 30 of 41)

- [Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects](https://mlsanity.com/paper/2412.00518/) (2024)
- [Rethinking Score Distillation as a Bridge Between Image Distributions](https://mlsanity.com/paper/2406.09417/) (2024)
- [Generating Physically Stable and Buildable Brick Structures from Text](https://mlsanity.com/paper/2505.05469/) (2025)
- [InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment](https://mlsanity.com/paper/2503.18454/) (2025)
- [Rectified-CFG++ for Flow Based Models](https://mlsanity.com/paper/2510.07631/) (2025)
- [Geometry in Style: 3D Stylization via Surface Normal Deformation](https://mlsanity.com/paper/2503.23241/) (2025)
- [Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization](https://mlsanity.com/paper/2504.02817/) (2025)
- [Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters](https://mlsanity.com/paper/2506.14530/) (2025)
- [DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape Matching](https://mlsanity.com/paper/2507.23715/) (2025)
- [CurveFlow: Curvature-Guided Flow Matching for Image Generation](https://mlsanity.com/paper/2508.15093/) (2025)
- [StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces](https://mlsanity.com/paper/2501.15445/) (2025)
- [SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent Trajectories](https://mlsanity.com/paper/2502.16972/) (2025)
- [GaussianFluent: Gaussian Simulation for Dynamic Scenes with Mixed Materials](https://mlsanity.com/paper/2601.09265/) (2026)
- [One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies](https://mlsanity.com/paper/2603.12480/) (2026)
- [DiMeR: Disentangled Mesh Reconstruction Model](https://mlsanity.com/paper/2504.17670/) (2025)
- [Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond](https://mlsanity.com/paper/2505.04621/) (2025)
- [FRIDU: Functional Map Refinement with Guided Image Diffusion](https://mlsanity.com/paper/2506.14322/) (2025)
- [GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction](https://mlsanity.com/paper/2512.25073/) (2025)
- [Text-to-3D Generation by 2D Editing](https://mlsanity.com/paper/2412.05929/) (2024)
- [ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion](https://mlsanity.com/paper/2502.02187/) (2025)
- [ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation](https://mlsanity.com/paper/2504.02316/) (2025)
- [3D PixBrush: Image-Guided Local Texture Synthesis](https://mlsanity.com/paper/2507.03731/) (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)
- [Text-to-3D Generation using Jensen-Shannon Score Distillation](https://mlsanity.com/paper/2503.10660/) (2025)
- [Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling](https://mlsanity.com/paper/2510.23605/) (2025)
- [Mean-Shift Distillation for Diffusion Mode Seeking](https://mlsanity.com/paper/2502.15989/) (2025)
- [InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalization](https://mlsanity.com/paper/2511.14899/) (2025)
- [SV-GS: Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splatting](https://mlsanity.com/paper/2601.00285/) (2026)
- [THOM: Generating Physically Plausible Hand-Object Meshes From Text](https://mlsanity.com/paper/2604.02736/) (2026)

## Abstract (arXiv)

While 2D diffusion models generate realistic, high-detail images, 3D shape generation methods like Score Distillation Sampling (SDS) built on these 2D diffusion models produce cartoon-like, over-smoothed shapes. To help explain this discrepancy, we show that the image guidance used in Score Distillation can be understood as the velocity field of a 2D denoising generative process, up to the choice of a noise term. In particular, after a change of variables, SDS resembles a high-variance version of Denoising Diffusion Implicit Models (DDIM) with a differently-sampled noise term: SDS introduces noise i.i.d. randomly at each step, while DDIM infers it from the previous noise predictions. This excessive variance can lead to over-smoothing and unrealistic outputs. We show that a better noise approximation can be recovered by inverting DDIM in each SDS update step. This modification makes SDS's generative process for 2D images almost identical to DDIM. In 3D, it removes over-smoothing, preserves higher-frequency detail, and brings the generation quality closer to that of 2D samplers. Experimentally, our method achieves better or similar 3D generation quality compared to other state-of-the-art Score Distillation methods, all without training additional neural networks or multi-view supervision, and providing useful insights into relationship between 2D and 3D asset generation with diffusion models.