Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views

• URL: http://arxiv.org/abs/2312.04424v2
• Date: Thu, 8 Aug 2024 03:01:31 GMT
• Title: Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views
• Authors: Yabo Chen, Jiemin Fang, Yuyang Huang, Taoran Yi, Xiaopeng Zhang, Lingxi Xie, Xinggang Wang, Wenrui Dai, Hongkai Xiong, Qi Tian,
• Abstract summary: Zero-1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to the 3D scope. But due to the high sparsity of the single input image, Zero-1-to-3 tends to produce geometry and appearance inconsistency across views. We propose to supply more condition information for the generation model but in a self-prompt way.
• Score: 119.76225283008579
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Synthesizing multi-view 3D from one single image is a significant but challenging task. Zero-1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to the 3D scope. The target view image is generated with a single-view source image and the camera pose as condition information. However, due to the high sparsity of the single input image, Zero-1-to-3 tends to produce geometry and appearance inconsistency across views, especially for complex objects. To tackle this issue, we propose to supply more condition information for the generation model but in a self-prompt way. A cascade framework is constructed with two Zero-1-to-3 models, named Cascade-Zero123, which progressively extract 3D information from the source image. Specifically, several nearby views are first generated by the first model and then fed into the second-stage model along with the source image as generation conditions. With amplified self-prompted condition images, our Cascade-Zero123 generates more consistent novel-view images than Zero-1-to-3. Experiment results demonstrate remarkable promotion, especially for various complex and challenging scenes, involving insects, humans, transparent objects, and stacked multiple objects etc. More demos and code are available at https://cascadezero123.github.io.

Related papers

• Free3D: Consistent Novel View Synthesis without 3D Representation [63.931920010054064]
  Free3D is a simple accurate method for monocular open-set novel view synthesis (NVS) Compared to other works that took a similar approach, we obtain significant improvements without resorting to an explicit 3D representation.
  arXiv  Detail & Related papers  (2023-12-07T18:59:18Z)
• Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model [30.44339780026541]
  Zero123++ is an image-conditioned diffusion model for generating 3D-consistent multi-view images from a single input view. We develop various conditioning and training schemes to minimize the effort of finetuning from off-the-shelf image diffusion models.
  arXiv  Detail & Related papers  (2023-10-23T17:18:59Z)
• ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion [61.37481051263816]
  Given a single image of a 3D object, this paper proposes a method (named ConsistNet) that is able to generate multiple images of the same object. Our method effectively learns 3D consistency over a frozen Zero123 backbone and can generate 16 surrounding views of the object within 40 seconds on a single A100 GPU.
  arXiv  Detail & Related papers  (2023-10-16T12:29:29Z)
• Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models [16.326276673056334]
  Consistent-1-to-3 is a generative framework that significantly mitigates this issue. We decompose the NVS task into two stages: (i) transforming observed regions to a novel view, and (ii) hallucinating unseen regions. We propose to employ epipolor-guided attention to incorporate geometry constraints, and multi-view attention to better aggregate multi-view information.
  arXiv  Detail & Related papers  (2023-10-04T17:58:57Z)
• Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data [76.38261311948649]
  Viewset Diffusion is a diffusion-based generator that outputs 3D objects while only using multi-view 2D data for supervision. We train a diffusion model to generate viewsets, but design the neural network generator to reconstruct internally corresponding 3D models. The model performs reconstruction efficiently, in a feed-forward manner, and is trained using only rendering losses using as few as three views per viewset.
  arXiv  Detail & Related papers  (2023-06-13T16:18:51Z)
• 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)
• Vision Transformer for NeRF-Based View Synthesis from a Single Input Image [49.956005709863355]
  We propose to leverage both the global and local features to form an expressive 3D representation. To synthesize a novel view, we train a multilayer perceptron (MLP) network conditioned on the learned 3D representation to perform volume rendering. Our method can render novel views from only a single input image and generalize across multiple object categories using a single model.
  arXiv  Detail & Related papers  (2022-07-12T17:52:04Z)
• CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields [67.76151996543588]
  We learn a 3D- and camera-aware generative model which faithfully recovers not only the image but also the camera data distribution. At test time, our model generates images with explicit control over the camera as well as the shape and appearance of the scene.
  arXiv  Detail & Related papers  (2021-03-31T17:59:24Z)

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.