DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis

• URL: http://arxiv.org/abs/2312.13016v4
• Date: Tue, 19 Mar 2024 23:01:59 GMT
• Title: DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis
• Authors: Yuming Gu, You Xie, Hongyi Xu, Guoxian Song, Yichun Shi, Di Chang, Jing Yang, Linjie Luo,
• Abstract summary: We present DiffPortrait3D, a conditional diffusion model capable of synthesizing 3D-consistent photo-realistic novel views. Given a single RGB input, we aim to synthesize plausible but consistent facial details rendered from novel camera views. We demonstrate state-of-the-art results both qualitatively and quantitatively on our challenging in-the-wild and multi-view benchmarks.
• Score: 18.64688172651478
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We present DiffPortrait3D, a conditional diffusion model that is capable of synthesizing 3D-consistent photo-realistic novel views from as few as a single in-the-wild portrait. Specifically, given a single RGB input, we aim to synthesize plausible but consistent facial details rendered from novel camera views with retained both identity and facial expression. In lieu of time-consuming optimization and fine-tuning, our zero-shot method generalizes well to arbitrary face portraits with unposed camera views, extreme facial expressions, and diverse artistic depictions. At its core, we leverage the generative prior of 2D diffusion models pre-trained on large-scale image datasets as our rendering backbone, while the denoising is guided with disentangled attentive control of appearance and camera pose. To achieve this, we first inject the appearance context from the reference image into the self-attention layers of the frozen UNets. The rendering view is then manipulated with a novel conditional control module that interprets the camera pose by watching a condition image of a crossed subject from the same view. Furthermore, we insert a trainable cross-view attention module to enhance view consistency, which is further strengthened with a novel 3D-aware noise generation process during inference. We demonstrate state-of-the-art results both qualitatively and quantitatively on our challenging in-the-wild and multi-view benchmarks.

Related papers

• Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion [63.81544586407943]
  Single-image 3D portrait generation methods typically employ 2D diffusion models to provide multi-view knowledge, which is then distilled into 3D representations. We propose a Hybrid Priors Diffsion model, which explicitly and implicitly incorporates multi-view priors as conditions to enhance the status consistency of the generated multi-view portraits. Experiments demonstrate that our method can produce 3D portraits with accurate geometry and rich details from a single image.
  arXiv  Detail & Related papers  (2024-11-15T17:19:18Z)
• MultiDiff: Consistent Novel View Synthesis from a Single Image [60.04215655745264]
  MultiDiff is a novel approach for consistent novel view synthesis of scenes from a single RGB image. Our results demonstrate that MultiDiff outperforms state-of-the-art methods on the challenging, real-world datasets RealEstate10K and ScanNet.
  arXiv  Detail & Related papers  (2024-06-26T17:53:51Z)
• Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models [24.301334966272297]
  We propose a novel generative model capable of producing a sequence of photorealistic images consistent with a specified camera trajectory. To measure the consistency over a sequence of generated views, we introduce a new metric, the thresholded symmetric epipolar distance (TSED)
  arXiv  Detail & Related papers  (2023-04-21T02:01:02Z)
• Zero-1-to-3: Zero-shot One Image to 3D Object [30.455300183998247]
  We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image. Our conditional diffusion model uses a synthetic dataset to learn controls of the relative camera viewpoint. Our method significantly outperforms state-of-the-art single-view 3D reconstruction and novel view synthesis models by leveraging Internet-scale pre-training.
  arXiv  Detail & Related papers  (2023-03-20T17:59:50Z)
• DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models [91.94566873400277]
  DiffDreamer is an unsupervised framework capable of synthesizing novel views depicting a long camera trajectory. We show that image-conditioned diffusion models can effectively perform long-range scene extrapolation while preserving consistency significantly better than prior GAN-based methods.
  arXiv  Detail & Related papers  (2022-11-22T10:06:29Z)
• Novel View Synthesis with Diffusion Models [56.55571338854636]
  We present 3DiM, a diffusion model for 3D novel view synthesis. It is able to translate a single input view into consistent and sharp completions across many views. 3DiM can generate multiple views that are 3D consistent using a novel technique called conditioning.
  arXiv  Detail & Related papers  (2022-10-06T16:59:56Z)
• Explicitly Controllable 3D-Aware Portrait Generation [42.30481422714532]
  We propose a 3D portrait generation network that produces consistent portraits according to semantic parameters regarding pose, identity, expression and lighting. Our method outperforms prior arts in extensive experiments, producing realistic portraits with vivid expression in natural lighting when viewed in free viewpoint.
  arXiv  Detail & Related papers  (2022-09-12T17:40:08Z)
• GAUDI: A Neural Architect for Immersive 3D Scene Generation [67.97817314857917]
  GAUDI is a generative model capable of capturing the distribution of complex and realistic 3D scenes that can be rendered immersively from a moving camera. We show that GAUDI obtains state-of-the-art performance in the unconditional generative setting across multiple datasets.
  arXiv  Detail & Related papers  (2022-07-27T19:10:32Z)
• LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space [90.74976459491303]
  We introduce a prior model that is conditioned on the runtime inputs and tie this prior space to the 3D face model via a normalizing flow in the latent space. A normalizing flow bridges the two representation spaces and transforms latent samples from one domain to another, allowing us to define a latent likelihood objective. We show that our approach leads to an expressive and effective prior, capturing facial dynamics and subtle expressions better.
  arXiv  Detail & Related papers  (2022-03-15T13:22:57Z)
• FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold [5.462226912969161]
  Current Generative Adversarial Networks (GANs) produce photorealistic renderings of portrait images. We show how our approach enables the integration of a pre-trained StyleGAN into standard 3D rendering pipelines. Our solution proposes the first truly free-viewpoint rendering of realistic faces at interactive rates.
  arXiv  Detail & Related papers  (2021-09-20T08:59:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.