ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation

By Peng Wang, Yichun Shi. arXiv.org, 2023

297 citations recorded by the source corpus.

We introduce"ImageDream,"an innovative image-prompt, multi-view diffusion model for 3D object generation. ImageDream stands out for its ability to produce 3D models of higher quality compared to existing state-of-the-art, image-conditioned methods. Our approach utilizes a canonical camera coordination for the objects in images, improving visual geometry accuracy. The model is designed with various levels of control at each block inside the diffusion model based on the input image, where global control shapes the overall object layout and local control fine-tunes the image details. The effectiveness of ImageDream is demonstrated through extensive evaluations using a standard prompt list. For more information, visit our project page at https://Image-Dream.github.io.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4c8608124dd92b84effedb7dd1965aeb13420e9c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

CAT3D: Create Anything in 3D with Multi-View Diffusion Models (2024, methodology): “On images with segmented objects, our geometry is often worse than existing approaches like ImageDream [9] and DreamCraft3D [81], but maintains competitive CLIP scores.”
Recent advances in 3D Gaussian splatting (2024, unknown): “It is promising to extract geometry, texture, and lighting with more advanced rendering techniques to facilitate independent editing and build the connection between 3DGS and mesh-based representation to enable efficient editing.”
LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation (2024, methodology): “Recently, several methods [20, 27, 43, 44, 51] propose to fine-tune multi-view diffusion models on 3D datasets to incorporate camera poses as an additional input.”
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models (2024, methodology): “…our sparse-view reconstruction model accepts free-viewpoint images as input, so we can integrate arbitrary multi-view generation model into our framework, e.g ., MVDream [43], ImageDream [51], SyncDreamer [24], SPAD [17] and SV3D [48], to achieve both text-to-3D and image-to-3D assets creation.”
Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation (2025, unknown): “Most works force the multi-view generated latents to communicate with each other by manipulating the self-attention layers with 3D-aware masks [36, 48, 88, 60, 95, 79, 78, 55].”
Qwen-Image Technical Report (2025, unknown): “Zero123 (Liu et al., 2023) 13.48 0.854 0.166 ImageDream (Wang &Shi, 2023) 15.22 0.883 0.164 CRM (Wang et al., 2024b) 15.93 0.891 0.152 with the ground truth image.”