Authors
Zibo Zhao, Wen Liu, Xin Chen, Xianfang Zeng, Rui Wang, Pei Cheng, Bin Fu, Tao Chen, Gang Yu, Shenghua Gao
ShanghaiTech University; Tencent PCG; Fudan University
Portals
Abstract
We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts. Directly learning a conditional generative model from images or texts to 3D shapes is prone to producing inconsistent results with the conditions because 3D shapes have an additional dimension whose distribution significantly differs from that of 2D images and texts. To bridge the domain gap among the three modalities and facilitate multi-modal-conditioned 3D shape generation, we explore representing 3D shapes in a shape-image-text-aligned space. Our framework comprises two models: a Shape-Image-Text-Aligned Variational Auto-Encoder (SITA-VAE) and a conditional Aligned Shape Latent Diffusion Model (ASLDM). The former model encodes the 3D shapes into the shape latent space aligned to the image and text and reconstructs the fine-grained 3D neural fields corresponding to given shape embeddings via the transformer-based decoder. The latter model learns a probabilistic mapping function from the image or text space to the latent shape space. Our extensive experiments demonstrate that our proposed approach can generate higher-quality and more diverse 3D shapes that better semantically conform to the visual or textural conditional inputs, validating the effectiveness of the shape-image-text-aligned space for cross-modality 3D shape generation.
Related Works
Neural 3D Shape Representation; Conditional 3D Shape Generation; Contrastive Learning in 3D
Comparisons
Occ, ConvOcc, IFNet, 3DILG, 3DS2V
Overview
Our method contains two models: the ShapeImage-Text-Aligned Variational Auto-Encoder (SITA-VAE) and the Aligned Shape Latent Diffusion Model (ASLDM). The SITA-VAE consists of four modules: an image encoder, a text encoder, a 3D shape encoder, and a 3D shape decoder. Encoders encode inputs pair into an aligned space, and the 3D shape decoder reconstructs 3D shapes given embeddings from the aligned space. The ASLDM maps the image or text condition to the aligned shape latent space for sampling a high-quality 3D shape embedding, which latterly reconstructed to high-fidelity 3D shapes by the 3D shape decoder.