GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers

• URL: http://arxiv.org/abs/2310.10375v3
• Date: Fri, 7 Jun 2024 12:47:50 GMT
• Title: GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers
• Authors: Takeru Miyato, Bernhard Jaeger, Max Welling, Andreas Geiger,
• Abstract summary: We argue that existing positional encoding schemes are suboptimal for 3D vision tasks. We propose a geometry-aware attention mechanism that encodes the geometric structure of tokens as relative transformation. We show that our attention, called Geometric Transform Attention (GTA), improves learning efficiency and performance of state-of-the-art transformer-based NVS models.
• Score: 63.41460219156508
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: As transformers are equivariant to the permutation of input tokens, encoding the positional information of tokens is necessary for many tasks. However, since existing positional encoding schemes have been initially designed for NLP tasks, their suitability for vision tasks, which typically exhibit different structural properties in their data, is questionable. We argue that existing positional encoding schemes are suboptimal for 3D vision tasks, as they do not respect their underlying 3D geometric structure. Based on this hypothesis, we propose a geometry-aware attention mechanism that encodes the geometric structure of tokens as relative transformation determined by the geometric relationship between queries and key-value pairs. By evaluating on multiple novel view synthesis (NVS) datasets in the sparse wide-baseline multi-view setting, we show that our attention, called Geometric Transform Attention (GTA), improves learning efficiency and performance of state-of-the-art transformer-based NVS models without any additional learned parameters and only minor computational overhead.

Related papers

• A Recipe for Geometry-Aware 3D Mesh Transformers [2.0992612407358293]
  We study an approach for embedding features at the patch level, accommodating patches with variable node counts. Our research highlights critical insights: 1) the importance of structural and positional embeddings facilitated by heat diffusion in general 3D mesh transformers; 2) the effectiveness of novel components such as geodesic masking and feature interaction via cross-attention in enhancing learning; and 3) the superior performance and efficiency of our proposed methods in challenging segmentation and classification tasks.
  arXiv  Detail & Related papers  (2024-10-31T19:13:31Z)
• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers [97.75725574963197]
  We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. We show that a sequence of such transformations induces a single linear transformation that faithfully summarises the full model computations. We show that the resulting explanations are of high visual quality and perform well under quantitative interpretability metrics.
  arXiv  Detail & Related papers  (2023-06-19T12:54:28Z)
• Vision Transformer with Quadrangle Attention [76.35955924137986]
  We propose a novel quadrangle attention (QA) method that extends the window-based attention to a general quadrangle formulation. Our method employs an end-to-end learnable quadrangle regression module that predicts a transformation matrix to transform default windows into target quadrangles. We integrate QA into plain and hierarchical vision transformers to create a new architecture named QFormer, which offers minor code modifications and negligible extra computational cost.
  arXiv  Detail & Related papers  (2023-03-27T11:13:50Z)
• Geometry-biased Transformers for Novel View Synthesis [36.11342728319563]
  We tackle the task of synthesizing novel views of an object given a few input images and associated camera viewpoints. Our work is inspired by recent 'geometry-free' approaches where multi-view images are encoded as a (global) set-latent representation. We propose 'Geometry-biased Transformers' (GBTs) that incorporate geometric inductive biases in the set-latent representation-based inference.
  arXiv  Detail & Related papers  (2023-01-11T18:59:56Z)
• Depth Field Networks for Generalizable Multi-view Scene Representation [31.090289865520475]
  We learn an implicit, multi-view consistent scene representation, introducing a series of 3D data augmentation techniques as a geometric inductive prior to increase view diversity. Our Depth Field Networks (DeFiNe) achieve state-of-the-art results in stereo and video depth estimation without explicit geometric constraints, and improve on zero-shot domain generalization by a wide margin.
  arXiv  Detail & Related papers  (2022-07-28T17:59:31Z)
• Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
  The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism. We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies. We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
  arXiv  Detail & Related papers  (2021-12-14T13:14:24Z)
• Learnable Fourier Features for Multi-DimensionalSpatial Positional Encoding [96.9752763607738]
  We propose a novel positional encoding method based on learnable Fourier features. Our experiments show that our learnable feature representation for multi-dimensional positional encoding outperforms existing methods.
  arXiv  Detail & Related papers  (2021-06-05T04:40:18Z)

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.