DeepAI AI Chat
Log In Sign Up

Learning to Generate Dense Point Clouds with Textures on Multiple Categories

by   Tao Hu, et al.
University of Maryland

3D reconstruction from images is a core problem in computer vision. With recent advances in deep learning, it has become possible to recover plausible 3D shapes even from single RGB images for the first time. However, obtaining detailed geometry and texture for objects with arbitrary topology remains challenging. In this paper, we propose a novel approach for reconstructing point clouds from RGB images. Unlike other methods, we can recover dense point clouds with hundreds of thousands of points, and we also include RGB textures. In addition, we train our model on multiple categories which leads to superior generalization to unseen categories compared to previous techniques. We achieve this using a two-stage approach, where we first infer an object coordinate map from the input RGB image, and then obtain the final point cloud using a reprojection and completion step. We show results on standard benchmarks that demonstrate the advantages of our technique. Code is available at


page 2

page 4

page 7

page 8

page 12


PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows

As 3D point clouds become the representation of choice for multiple visi...

Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion

Point clouds captured by scanning devices are often incomplete due to oc...

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 activ...

Pre-Training by Completing Point Clouds

There has recently been a flurry of exciting advances in deep learning m...

X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360^∘ Insufficient RGB-D Views

Neural Radiance Fields (NeRFs), despite their outstanding performance on...

Novel View Synthesis from Single Images via Point Cloud Transformation

In this paper the argument is made that for true novel view synthesis of...

Embodied Question Answering in Photorealistic Environments with Point Cloud Perception

To help bridge the gap between internet vision-style problems and the go...