Squeeze3D: Your 3D Generation Model is Secretly an Extreme Neural Compressor
Abstract
A novel framework called Squeeze3D uses pre-trained models to compress 3D data efficiently, achieving high compression ratios while maintaining visual quality.
We propose Squeeze3D, a novel framework that leverages implicit prior knowledge learnt by existing pre-trained 3D generative models to compress 3D data at extremely high compression ratios. Our approach bridges the latent spaces between a pre-trained encoder and a pre-trained generation model through trainable mapping networks. Any 3D model represented as a mesh, point cloud, or a radiance field is first encoded by the pre-trained encoder and then transformed (i.e. compressed) into a highly compact latent code. This latent code can effectively be used as an extremely compressed representation of the mesh or point cloud. A mapping network transforms the compressed latent code into the latent space of a powerful generative model, which is then conditioned to recreate the original 3D model (i.e. decompression). Squeeze3D is trained entirely on generated synthetic data and does not require any 3D datasets. The Squeeze3D architecture can be flexibly used with existing pre-trained 3D encoders and existing generative models. It can flexibly support different formats, including meshes, point clouds, and radiance fields. Our experiments demonstrate that Squeeze3D achieves compression ratios of up to 2187x for textured meshes, 55x for point clouds, and 619x for radiance fields while maintaining visual quality comparable to many existing methods. Squeeze3D only incurs a small compression and decompression latency since it does not involve training object-specific networks to compress an object.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (2025)
- Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets (2025)
- DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images (2025)
- Efficient Implicit Neural Compression of Point Clouds via Learnable Activation in Latent Space (2025)
- OSCAR: One-Step Diffusion Codec for Image Compression Across Multiple Bit-rates (2025)
- LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework (2025)
- Advancing high-fidelity 3D and Texture Generation with 2.5D latents (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper