Although deep networks-based 3D reconstruction methods can recover the 3D geometry given few inputs, they may produce unfaithful reconstruction when predicting occluded parts of 3D objects. To address the issue, we propose Detail-Enhanced Generative Adversarial Network (DEGAN) which consists of Encoder–Decoder-Based Generator (EDGen) and Voxel-Point Embedding Network-Based Discriminator (VPDis) for 3D reconstruction from a monocular depth image of an object. Firstly, EDGen decodes the features from the 2.5D voxel grid representation of an input depth image and generates the 3D occupancy grid under GAN losses and a sampling point loss. The sampling loss can improve the accuracy of predicted points with high uncertainty. VPDis helps reconstruct the details under voxel and point adversarial losses, respectively. Experimental results show that DEGAN not only outperforms several state-of-the-art methods on both public ModelNet and ShapeNet datasets but also predicts more reliable occluded/missing parts of 3D objects.

Inferring a complete 3D shape from a single-view image is an ill-posed problem. The proposed methods often have problems such as insufficient feature expression, unstable training and limited constraints, resulting in a low accuracy and ambiguity reconstruction. To address these problems, we propose a prior-guided adaptive probabilistic network for single-view 3D reconstruction, called PAPRec. In the training stage, PAPRec encodes a single-view image and its corresponding 3D prior into image feature distribution and point cloud feature distribution, respectively. PAPRec then utilizes a latent normalizing flow to fit the two distributions and obtains a latent vector with rich cues. PAPRec finally introduces an adaptive probabilistic network consisting of a shape normalizing flow and a diffusion model in order to decode the latent vector as a complete 3D point cloud. Unlike the proposed methods, PAPRec fully learns the global and local features of objects by innovatively integrating 3D prior guidance and the adaptive probability network under the optimization of a loss function combining prior, flow and diffusion losses. The experimental results on the public ShapeNet dataset show that PAPRec, on average, improves CD by 2.62%, EMD by 5.99% and F1 by 4.41%, in comparison to several state-of-the-art methods.

With the widespread adoption of 3D scanning technology, depth view-driven 3D reconstruction has become crucial for applications such as SLAM, virtual reality, and autonomous vehicles. However, due to the effects of self-occlusion and environmental occlusion, obtaining complete and error-free 3D shapes directly from 3D scans remains challenging, as previous reconstruction methods tend to lose details. To this end, we propose Dynamic Quality Refinement Network (DQRNet) for reconstructing complete and accurate 3D shape from a single depth view. DQRNet introduces a dynamic encoder–decoder and a detail quality refiner to generate high-resolution 3D shapes, where the former designs a dynamic latent extractor to adaptively select important parts of an object and the latter designs global and local point refiners to enhance the reconstruction quality. Experimental results show that DQRNet is able to focus on capturing the details at boundaries and key areas on ShapeNet dataset, thereby achieving better accuracy and robustness than SOTA methods.

Three-dimensional (3D) reconstruction serves as a key technology bridging the real and digital worlds, with broad application in remote sensing, autonomous driving, and robotics. In recent years, its technical paradigm has shifted from geometry-based methods to data-driven approaches, with diffusion models emerging as a major driving force due to their stable training process, strong ability to learn priors from large-scale datasets, and excellent controllability over outputs. Despite the proliferation of diverse architectures, a systematic analysis and comparison of these methods remains absent. In this paper, we present a comprehensive review of diffusion-based 3D reconstruction methods. Based on the space where diffusion operates, we first categorize existing approaches into four types—image diffusion, latent diffusion, 3D diffusion, and hybrid diffusion—and we provide a detailed analysis of their methodologies. We then summarize commonly used 3D datasets and provide a comparative evaluation of these methods across three dimensions: reconstruction accuracy, computational efficiency, and generalization capabilities. Finally, we discuss future developments of diffusion-based 3D reconstruction methods.