MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes

• URL: http://arxiv.org/abs/2412.11457v2
• Date: Sat, 22 Mar 2025 12:34:37 GMT
• Title: MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes
• Authors: Ruijie Lu, Yixin Chen, Junfeng Ni, Baoxiong Jia, Yu Liu, Diwen Wan, Gang Zeng, Siyuan Huang,
• Abstract summary: MOVIS aims to enhance the structural awareness of the view-conditioned diffusion model for multi-object NVS.<n>We introduce an auxiliary task requiring the model to simultaneously predict novel view object masks.<n>Our method exhibits strong generalization capabilities and produces consistent novel view synthesis.
• Score: 35.16430027877207
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Repurposing pre-trained diffusion models has been proven to be effective for NVS. However, these methods are mostly limited to a single object; directly applying such methods to compositional multi-object scenarios yields inferior results, especially incorrect object placement and inconsistent shape and appearance under novel views. How to enhance and systematically evaluate the cross-view consistency of such models remains under-explored. To address this issue, we propose MOVIS to enhance the structural awareness of the view-conditioned diffusion model for multi-object NVS in terms of model inputs, auxiliary tasks, and training strategy. First, we inject structure-aware features, including depth and object mask, into the denoising U-Net to enhance the model's comprehension of object instances and their spatial relationships. Second, we introduce an auxiliary task requiring the model to simultaneously predict novel view object masks, further improving the model's capability in differentiating and placing objects. Finally, we conduct an in-depth analysis of the diffusion sampling process and carefully devise a structure-guided timestep sampling scheduler during training, which balances the learning of global object placement and fine-grained detail recovery. To systematically evaluate the plausibility of synthesized images, we propose to assess cross-view consistency and novel view object placement alongside existing image-level NVS metrics. Extensive experiments on challenging synthetic and realistic datasets demonstrate that our method exhibits strong generalization capabilities and produces consistent novel view synthesis, highlighting its potential to guide future 3D-aware multi-object NVS tasks. Our project page is available at https://jason-aplp.github.io/MOVIS/.

Related papers

• Novel View Synthesis with Pixel-Space Diffusion Models [4.844800099745365]
  generative models are being increasingly employed in novel view synthesis (NVS) We adapt a modern diffusion model architecture for end-to-end NVS in the pixel space. We introduce a novel NVS training scheme that utilizes single-view datasets, capitalizing on their relative abundance.
  arXiv  Detail & Related papers  (2024-11-12T12:58:33Z)
• Zero-Shot Object-Centric Representation Learning [72.43369950684057]
  We study current object-centric methods through the lens of zero-shot generalization. We introduce a benchmark comprising eight different synthetic and real-world datasets. We find that training on diverse real-world images improves transferability to unseen scenarios.
  arXiv  Detail & Related papers  (2024-08-17T10:37:07Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• pix2gestalt: Amodal Segmentation by Synthesizing Wholes [34.45464291259217]
  pix2gestalt is a framework for zero-shot amodal segmentation. We learn a conditional diffusion model for reconstructing whole objects in challenging zero-shot cases.
  arXiv  Detail & Related papers  (2024-01-25T18:57:36Z)
• FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects [55.77542145604758]
  FoundationPose is a unified foundation model for 6D object pose estimation and tracking. Our approach can be instantly applied at test-time to a novel object without fine-tuning.
  arXiv  Detail & Related papers  (2023-12-13T18:28:09Z)
• Multi-View Unsupervised Image Generation with Cross Attention Guidance [23.07929124170851]
  This paper introduces a novel pipeline for unsupervised training of a pose-conditioned diffusion model on single-category datasets. We identify object poses by clustering the dataset through comparing visibility and locations of specific object parts. Our model, MIRAGE, surpasses prior work in novel view synthesis on real images.
  arXiv  Detail & Related papers  (2023-12-07T14:55:13Z)
• MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare [84.80956484848505]
  MegaPose is a method to estimate the 6D pose of novel objects, that is, objects unseen during training. We present a 6D pose refiner based on a render&compare strategy which can be applied to novel objects. Second, we introduce a novel approach for coarse pose estimation which leverages a network trained to classify whether the pose error between a synthetic rendering and an observed image of the same object can be corrected by the refiner.
  arXiv  Detail & Related papers  (2022-12-13T19:30:03Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• Conditional Object-Centric Learning from Video [34.012087337046005]
  We introduce a sequential extension to Slot Attention to predict optical flow for realistic looking synthetic scenes. We show that conditioning the initial state of this model on a small set of hints, such as center of mass of objects in the first frame, is sufficient to significantly improve instance segmentation. These benefits generalize beyond the training distribution to novel objects, novel backgrounds, and to longer video sequences.
  arXiv  Detail & Related papers  (2021-11-24T16:10:46Z)
• Salient Objects in Clutter [130.63976772770368]
  This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets. This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets. We propose a new high-quality dataset and update the previous saliency benchmark.
  arXiv  Detail & Related papers  (2021-05-07T03:49:26Z)
• Unsupervised Learning of 3D Object Categories from Videos in the Wild [75.09720013151247]
  We focus on learning a model from multiple views of a large collection of object instances. We propose a new neural network design, called warp-conditioned ray embedding (WCR), which significantly improves reconstruction. Our evaluation demonstrates performance improvements over several deep monocular reconstruction baselines on existing benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T17:57:01Z)
• Unsupervised Video Decomposition using Spatio-temporal Iterative Inference [31.97227651679233]
  Multi-object scene decomposition is a fast-emerging problem in learning. We show that our model has a high accuracy even without color information. We demonstrate the decomposition, segmentation prediction capabilities of our model and show that it outperforms the state-of-the-art on several benchmark datasets.
  arXiv  Detail & Related papers  (2020-06-25T22:57:17Z)

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.