Cycle-Consistent Generative Rendering for 2D-3D Modality Translation

For humans, visual understanding is inherently generative: given a 3D shape, we can postulate how it would look in the world; given a 2D image, we can infer the 3D structure that likely gave rise to it. We can thus translate between the 2D visual and 3D structural modalities of a given object. In the context of computer vision, this corresponds to a learnable module that serves two purposes: (i) generate a realistic rendering of a 3D object (shape-to-image translation) and (ii) infer a realistic 3D shape from an image (image-to-shape translation). In this paper, we learn such a module while being conscious of the difficulties in obtaining large paired 2D-3D datasets. By leveraging generative domain translation methods, we are able to define a learning algorithm that requires only weak supervision, with unpaired data. The resulting model is not only able to perform 3D shape, pose, and texture inference from 2D images, but can also generate novel textured 3D shapes and renders, similar to a graphics pipeline. More specifically, our method (i) infers an explicit 3D mesh representation, (ii) utilizes example shapes to regularize inference, (iii) requires only an image mask (no keypoints or camera extrinsics), and (iv) has generative capabilities. While prior work explores subsets of these properties, their combination is novel. We demonstrate the utility of our learned representation, as well as its performance on image generation and unpaired 3D shape inference tasks.


page 17

page 18

page 19

page 20

page 21

page 22


Visual Object Networks: Image Generation with Disentangled 3D Representation

Recent progress in deep generative models has led to tremendous breakthr...

Cartoon-to-real: An Approach to Translate Cartoon to Realistic Images using GAN

We propose a method to translate cartoon images to real world images usi...

Textured Neural Avatars

We present a system for learning full-body neural avatars, i.e. deep net...

ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images

The problem of inferring object shape from a single 2D image is undercon...

Latent feature disentanglement for 3D meshes

Generative modeling of 3D shapes has become an important problem due to ...

Shadows Shed Light on 3D Objects

3D reconstruction is a fundamental problem in computer vision, and the t...

GET3D–: Learning GET3D from Unconstrained Image Collections

The demand for efficient 3D model generation techniques has grown expone...

Code Repositories


Implementation of 2D-3D Cyclic Generative Renderer (3DV-2020).

view repo

Please sign up or login with your details

Forgot password? Click here to reset