{ "id": "2111.12731", "version": "v2", "published": "2021-11-24T19:00:07.000Z", "updated": "2022-02-20T17:28:21.000Z", "title": "Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering", "authors": [ "Guillaume Rochette", "Chris Russell", "Richard Bowden" ], "comment": "Accepted at Face and Gesture 2021, 8 pages, 7 figures", "categories": [ "cs.CV" ], "abstract": "We present a new approach for synthesizing novel views of people in new poses. Our novel differentiable renderer enables the synthesis of highly realistic images from any viewpoint. Rather than operating over mesh-based structures, our renderer makes use of diffuse Gaussian primitives that directly represent the underlying skeletal structure of a human. Rendering these primitives gives results in a high-dimensional latent image, which is then transformed into an RGB image by a decoder network. The formulation gives rise to a fully differentiable framework that can be trained end-to-end. We demonstrate the effectiveness of our approach to image reconstruction on both the Human3.6M and Panoptic Studio datasets. We show how our approach can be used for motion transfer between individuals; novel view synthesis of individuals captured from just a single camera; to synthesize individuals from any virtual viewpoint; and to re-render people in novel poses. Code and video results are available at https://github.com/GuillaumeRochette/HumanViewSynthesis.", "revisions": [ { "version": "v2", "updated": "2022-02-20T17:28:21.000Z" } ], "analyses": { "keywords": [ "novel view synthesis", "human pose manipulation", "differentiable rendering", "novel differentiable renderer enables", "individuals" ], "note": { "typesetting": "TeX", "pages": 8, "language": "en", "license": "arXiv", "status": "editable" } } }