RGB2Point: 3D Point Cloud Generation from Single RGB Images
We introduce RGB2Point, an unposed single-view RGB image to a 3D point cloud generation based on Transformer. RGB2Point takes an input image of an object and generates a dense 3D point cloud. Contrary to prior works based on CNN layers and diffusion denoising approaches, we use pre-trained Transformer layers that are fast and generate high-quality point clouds with consistent quality over available categories. Our generated point clouds demonstrate high quality on a real-world dataset, as evidenced by improved Chamfer distance (51.15%) and Earth Mover's distance (45.96%) metrics compared to the current state-of-the-art. Additionally, our approach shows a better quality on a synthetic dataset, achieving better Chamfer distance (39.26%), Earth Mover's distance (26.95%), and F-score (47.16%). Moreover, our method produces 63.1% more consistent high-quality results across various object categories compared to prior works. Furthermore, RGB2Point is computationally efficient, requiring only 2.3GB of VRAM to reconstruct a 3D point cloud from a single RGB image, and our implementation generates the results 15,133x faster than a SOTA diffusion-based model.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingPoint Cloud GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SE-MD: A Single-encoder multiple-decoder deep network for point cloud generation from 2D images
3D model generation from single 2D RGB images is a challenging and actively researched computer vision task. Various techniques using conventional network architectures have been proposed for the same. However, the body …
DecoderPoint Cloud GenerationInferring Point Clouds from Single Monocular Images by Depth Intermediation
In this paper, we propose a pipeline to generate 3D point cloud of an object from a single-view RGB image. Most previous work predict the 3D point coordinates from single RGB images directly. We decompose this problem in…
3D Object ReconstructionDepth EstimationObjectObject Reconstruction+1Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors
Recent progress in 3D generation has been driven largely by models conditioned on images or text, while readily available 3D priors are still underused. In many real-world scenarios, the visible-region point cloud are ea…
Scene Generation3D GenerationPoint CloudsRealPoint3D: Point Cloud Generation from a Single Image with Complex Background
3D point cloud generation by the deep neural network from a single image has been attracting more and more researchers' attention. However, recently-proposed methods require the objects be captured with relatively clean …
3D GenerationPoint Cloud GenerationA Hybrid Generative and Discriminative PointNet on Unordered Point Sets
As point cloud provides a natural and flexible representation usable in myriad applications (e.g., robotics and self-driving cars), the ability to synthesize point clouds for analysis becomes crucial. Recently, Xie et al…
image-classificationImage ClassificationPoint Cloud ClassificationPoint Cloud Generation+1