WorDepth: Variational Language Prior for Monocular Depth Estimation

• URL: http://arxiv.org/abs/2404.03635v4
• Date: Sun, 2 Jun 2024 04:56:32 GMT
• Title: WorDepth: Variational Language Prior for Monocular Depth Estimation
• Authors: Ziyao Zeng, Daniel Wang, Fengyu Yang, Hyoungseob Park, Yangchao Wu, Stefano Soatto, Byung-Woo Hong, Dong Lao, Alex Wong,
• Abstract summary: We investigate whether two inherently ambiguous modalities can be used in conjunction to produce metric-scaled reconstructions. We focus on monocular depth estimation, the problem of predicting a dense depth map from a single image. Our approach is trained alternatingly between the text and image branches.
• Score: 47.614203035800735
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Three-dimensional (3D) reconstruction from a single image is an ill-posed problem with inherent ambiguities, i.e. scale. Predicting a 3D scene from text description(s) is similarly ill-posed, i.e. spatial arrangements of objects described. We investigate the question of whether two inherently ambiguous modalities can be used in conjunction to produce metric-scaled reconstructions. To test this, we focus on monocular depth estimation, the problem of predicting a dense depth map from a single image, but with an additional text caption describing the scene. To this end, we begin by encoding the text caption as a mean and standard deviation; using a variational framework, we learn the distribution of the plausible metric reconstructions of 3D scenes corresponding to the text captions as a prior. To "select" a specific reconstruction or depth map, we encode the given image through a conditional sampler that samples from the latent space of the variational text encoder, which is then decoded to the output depth map. Our approach is trained alternatingly between the text and image branches: in one optimization step, we predict the mean and standard deviation from the text description and sample from a standard Gaussian, and in the other, we sample using a (image) conditional sampler. Once trained, we directly predict depth from the encoded text using the conditional sampler. We demonstrate our approach on indoor (NYUv2) and outdoor (KITTI) scenarios, where we show that language can consistently improve performance in both.

Related papers

• PriorDiffusion: Leverage Language Prior in Diffusion Models for Monocular Depth Estimation [10.856377349228927]
  We argue that language priors can enhance monocular depth estimation by leveraging the geometric prior aligned with the language description. We propose PriorDiffusion, using a pre-trained text-to-image diffusion model that takes both image and text description that aligned with the scene to infer affine-invariant depth. We show that language priors can guide the model's attention to specific regions and help it perceive the 3D scene in alignment with user intent.
  arXiv  Detail & Related papers  (2024-11-24T05:07:10Z)
• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images [100.80376573969045]
  NoPoSplat is a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from multi-view images. Our model achieves real-time 3D Gaussian reconstruction during inference. This work makes significant advances in pose-free generalizable 3D reconstruction and demonstrates its applicability to real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-31T17:58:22Z)
• Directional Texture Editing for 3D Models [51.31499400557996]
  ITEM3D is designed for automatic textbf3D object editing according to the text textbfInstructions. Leveraging the diffusion models and the differentiable rendering, ITEM3D takes the rendered images as the bridge of text and 3D representation.
  arXiv  Detail & Related papers  (2023-09-26T12:01:13Z)
• SketchSampler: Sketch-based 3D Reconstruction via View-dependent Depth Sampling [75.957103837167]
  Reconstructing a 3D shape based on a single sketch image is challenging due to the large domain gap between a sparse, irregular sketch and a regular, dense 3D shape. Existing works try to employ the global feature extracted from sketch to directly predict the 3D coordinates, but they usually suffer from losing fine details that are not faithful to the input sketch.
  arXiv  Detail & Related papers  (2022-08-14T16:37:51Z)
• OptGAN: Optimizing and Interpreting the Latent Space of the Conditional Text-to-Image GANs [8.26410341981427]
  We study how to ensure that generated samples are believable, realistic or natural. We present a novel algorithm which identifies semantically-understandable directions in the latent space of a conditional text-to-image GAN architecture.
  arXiv  Detail & Related papers  (2022-02-25T20:00:33Z)
• Learning to Recover 3D Scene Shape from a Single Image [98.20106822614392]
  We propose a two-stage framework that first predicts depth up to an unknown scale and shift from a single monocular image. We then use 3D point cloud encoders to predict the missing depth shift and focal length that allow us to recover a realistic 3D scene shape.
  arXiv  Detail & Related papers  (2020-12-17T02:35:13Z)
• Coherent Reconstruction of Multiple Humans from a Single Image [68.3319089392548]
  In this work, we address the problem of multi-person 3D pose estimation from a single image. A typical regression approach in the top-down setting of this problem would first detect all humans and then reconstruct each one of them independently. Our goal is to train a single network that learns to avoid these problems and generate a coherent 3D reconstruction of all the humans in the scene.
  arXiv  Detail & Related papers  (2020-06-15T17:51:45Z)

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.