# CorrespondentDream: Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences

arXiv: https://arxiv.org/abs/2404.10603 · HTML: https://mlsanity.com/paper/2404.10603/

## Key facts

- Cited by 6 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 33 of its 39 references that are in the map.
- First posted on arXiv 16 Apr 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 33)

- [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)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [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)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (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)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields](https://mlsanity.com/paper/2112.03907/) (2021)
- [Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis](https://mlsanity.com/paper/2104.00677/) (2021)
- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [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)
- [Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion](https://mlsanity.com/paper/2212.06135/) (2022)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)
- [Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence](https://mlsanity.com/paper/2305.14334/) (2023)
- [Self-Calibrating Neural Radiance Fields](https://mlsanity.com/paper/2108.13826/) (2021)
- [SPARF: Neural Radiance Fields from Sparse and Noisy Poses](https://mlsanity.com/paper/2211.11738/) (2022)
- [Neighbourhood Consensus Networks](https://mlsanity.com/paper/1810.10510/) (2018)
- [Unsupervised Semantic Correspondence Using Stable Diffusion](https://mlsanity.com/paper/2305.15581/) (2023)
- [Learning Accurate Dense Correspondences and When to Trust Them](https://mlsanity.com/paper/2101.01710/) (2021)
- [Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data](https://mlsanity.com/paper/2306.07881/) (2023)
- [HoloDiffusion: Training a 3D Diffusion Model using 2D Images](https://mlsanity.com/paper/2303.16509/) (2023)
- [NerfAcc: Efficient Sampling Accelerates NeRFs](https://mlsanity.com/paper/2305.04966/) (2023)
- [Leveraging 2D Data to Learn Textured 3D Mesh Generation](https://mlsanity.com/paper/2004.04180/) (2020)

## Built on by (most cited first, 6 of 6)

- [FreeAction: Training-Free Techniques for Enhanced Fidelity of Trajectory-to-Video Generation](https://mlsanity.com/paper/2509.24241/) (2025)
- [Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards](https://mlsanity.com/paper/2603.00918/) (2026)
- [Similarity-Aware Selective State-Space Modeling for Semantic Correspondence](https://mlsanity.com/paper/2509.24318/) (2025)
- [Harnessing the Power of Training-Free Techniques in Text-to-2D Generation for Text-to-3D Generation via Score Distillation Sampling](https://mlsanity.com/paper/2505.19868/) (2025)
- [RapidMV: Leveraging Spatio-Angular Representations for Efficient and Consistent Text-to-Multi-View Synthesis](https://mlsanity.com/paper/2509.24410/) (2025)
- [Geometrically Consistent Multi-View Scene Generation from Freehand Sketches](https://mlsanity.com/paper/2604.14302/) (2026)

## Abstract (arXiv)

Leveraging multi-view diffusion models as priors for 3D optimization have alleviated the problem of 3D consistency, e.g., the Janus face problem or the content drift problem, in zero-shot text-to-3D models. However, the 3D geometric fidelity of the output remains an unresolved issue; albeit the rendered 2D views are realistic, the underlying geometry may contain errors such as unreasonable concavities. In this work, we propose CorrespondentDream, an effective method to leverage annotation-free, cross-view correspondences yielded from the diffusion U-Net to provide additional 3D prior to the NeRF optimization process. We find that these correspondences are strongly consistent with human perception, and by adopting it in our loss design, we are able to produce NeRF models with geometries that are more coherent with common sense, e.g., more smoothed object surface, yielding higher 3D fidelity. We demonstrate the efficacy of our approach through various comparative qualitative results and a solid user study.