Learning Gaussian Representation for Eye Fixation Prediction
- URL: http://arxiv.org/abs/2403.14821v1
- Date: Thu, 21 Mar 2024 20:28:22 GMT
- Title: Learning Gaussian Representation for Eye Fixation Prediction
- Authors: Peipei Song, Jing Zhang, Piotr Koniusz, Nick Barnes,
- Abstract summary: Existing eye fixation prediction methods perform the mapping from input images to the corresponding dense fixation maps generated from raw fixation points.
We introduce Gaussian Representation for eye fixation modeling.
We design our framework upon some lightweight backbones to achieve real-time fixation prediction.
- Score: 54.88001757991433
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Existing eye fixation prediction methods perform the mapping from input images to the corresponding dense fixation maps generated from raw fixation points. However, due to the stochastic nature of human fixation, the generated dense fixation maps may be a less-than-ideal representation of human fixation. To provide a robust fixation model, we introduce Gaussian Representation for eye fixation modeling. Specifically, we propose to model the eye fixation map as a mixture of probability distributions, namely a Gaussian Mixture Model. In this new representation, we use several Gaussian distribution components as an alternative to the provided fixation map, which makes the model more robust to the randomness of fixation. Meanwhile, we design our framework upon some lightweight backbones to achieve real-time fixation prediction. Experimental results on three public fixation prediction datasets (SALICON, MIT1003, TORONTO) demonstrate that our method is fast and effective.
Related papers
- NovelGS: Consistent Novel-view Denoising via Large Gaussian Reconstruction Model [57.92709692193132]
NovelGS is a diffusion model for Gaussian Splatting given sparse-view images.
We leverage the novel view denoising through a transformer-based network to generate 3D Gaussians.
arXiv Detail & Related papers (2024-11-25T07:57:17Z) - 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) - Correntropy-Based Improper Likelihood Model for Robust Electrophysiological Source Imaging [18.298620404141047]
Existing source imaging algorithms utilize the Gaussian assumption for the observation noise to build the likelihood function for Bayesian inference.
The electromagnetic measurements of brain activity are usually affected by miscellaneous artifacts, leading to a potentially non-Gaussian distribution for the observation noise.
We propose a new likelihood model which is robust with respect to non-Gaussian noises.
arXiv Detail & Related papers (2024-08-27T07:54:15Z) - CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting [68.94594215660473]
We propose an efficient 3D scene representation, named Compressed Gaussian Splatting (CompGS)
We exploit a small set of anchor primitives for prediction, allowing the majority of primitives to be encapsulated into highly compact residual forms.
Experimental results show that the proposed CompGS significantly outperforms existing methods, achieving superior compactness in 3D scene representation without compromising model accuracy and rendering quality.
arXiv Detail & Related papers (2024-04-15T04:50:39Z) - pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction [26.72289913260324]
pixelSplat is a feed-forward model that learns to reconstruct 3D radiance fields parameterized by 3D Gaussian primitives from pairs of images.
Our model features real-time and memory-efficient rendering for scalable training as well as fast 3D reconstruction at inference time.
arXiv Detail & Related papers (2023-12-19T17:03:50Z) - DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models [5.908471365011943]
We propose emphDiffPose, a conditional diffusion model that predicts multiple hypotheses for a given input image.
We show that DiffPose slightly improves upon the state of the art for multi-hypothesis pose estimation for simple poses and outperforms it by a large margin for highly ambiguous poses.
arXiv Detail & Related papers (2022-11-29T18:55:13Z) - A Model for Multi-View Residual Covariances based on Perspective
Deformation [88.21738020902411]
We derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups.
We validate our model with synthetic and real data and integrate it into photometric and feature-based Bundle Adjustment.
arXiv Detail & Related papers (2022-02-01T21:21:56Z) - Probabilistic Modeling for Human Mesh Recovery [73.11532990173441]
This paper focuses on the problem of 3D human reconstruction from 2D evidence.
We recast the problem as learning a mapping from the input to a distribution of plausible 3D poses.
arXiv Detail & Related papers (2021-08-26T17:55:11Z)
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.