Search Results for author:
Found 48 papers, 18 papers with code
Joint 3D Layout and Depth Prediction from a Single Indoor Panorama Image
Leveraging the layout depth map as an intermediate representation, our proposed method outperforms existing methods for both panorama layout prediction and depth estimation.
LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting
Our approach makes two key contributions: a data curation strategy from the StyleGAN-based relighting model for our training, and a modified diffusion-based ControlNet that processes both latent intrinsic properties from the source image and latent extrinsic properties from the target image.
MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM
Unfortunately, existing methods are slow, cannot accurately render real-world data, are restricted to two agents, and have limited tracking accuracy.
FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
To address this, we present a 3D Gaussian-based novel view synthesis method using sparse input images that can accurately render the scene from the viewpoints not covered by the training images.
SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image
We evaluate SDFit on the Pix3D and Pascal3D+ datasets of real-world images.
RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Models
Specifically, RealDiff simulates a diffusion process at the missing object parts while conditioning the generation on the partial input to address the multimodal nature of the task.
Ray-Distance Volume Rendering for Neural Scene Reconstruction
To tackle this issue, our work proposes a novel approach for indoor scene reconstruction, which instead parameterizes the density function with the Signed Ray Distance Function (SRDF).
Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstruction
First, geometry-guided feature learning encodes geometric priors to contain view-dependent information.
ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining
In particular, we show that (1) the distribution of the optimized GS centroids significantly differs from the uniformly sampled point cloud (used for initialization) counterpart; (2) this change in distribution results in degradation in classification but improvement in segmentation tasks when using only the centroids; (3) to leverage additional Gaussian parameters, we propose Gaussian feature grouping in a normalized feature space, along with splats pooling layer, offering a tailored solution to effectively group and embed similar Gaussians, which leads to notable improvement in finetuning tasks.
SceneTeller: Language-to-3D Scene Generation
Designing high-quality indoor 3D scenes is important in many practical applications, such as room planning or game development.
Retinex-Diffusion: On Controlling Illumination Conditions in Diffusion Models via Retinex Theory
This paper introduces a novel approach to illumination manipulation in diffusion models, addressing the gap in conditional image generation with a focus on lighting conditions.
Auto-Vocabulary Segmentation for LiDAR Points
Existing perception methods for autonomous driving fall short of recognizing unknown entities not covered in the training data.
Modeling Weather Uncertainty for Multi-weather Co-Presence Estimation
In this paper, we start with solid revisit of the physics definition of weather and how it can be described as a continuous machine learning and computer vision task.
Learning Generalized Segmentation for Foggy-scenes by Bi-directional Wavelet Guidance
We argue that an ideal segmentation model that can be well generalized to foggy-scenes need to simultaneously enhance the content, de-correlate the urban-scene style and de-correlate the fog style.
T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning
The scarcity of annotated data in LiDAR point cloud understanding hinders effective representation learning.
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
We present a dense simultaneous localization and mapping (SLAM) method that uses 3D Gaussians as a scene representation.
Relational Prior Knowledge Graphs for Detection and Instance Segmentation
Humans have a remarkable ability to perceive and reason about the world around them by understanding the relationships between objects.
HaarNet: Large-scale Linear-Morphological Hybrid Network for RGB-D Semantic Segmentation
In the network, morphological Haar sampling is applied to both feature channels in several layers, which splits extreme values and high-frequency information such that both can be processed to improve both modalities.
Ranked #53 on
Semantic Segmentation
on NYU Depth v2
APNet: Urban-level Scene Segmentation of Aerial Images and Point Clouds
To leverage the different properties of each branch, we employ a geometry-aware fusion module that is learned to combine the results of each branch.
Intrinsic Image Decomposition Using Point Cloud Representation
The purpose of intrinsic decomposition is to separate an image into its albedo (reflective properties) and shading components (illumination properties).
Interactive Learning of Intrinsic and Extrinsic Properties for All-day Semantic Segmentation
In this paper, in contrast to existing methods, we tackle this challenge from the perspective of image formulation itself, where the image appearance is determined by both intrinsic (e. g., semantic category, structure) and extrinsic (e. g., lighting) properties.
Ranked #1 on
Semantic Segmentation
on Mapillary val
Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation
Unlike domain gap challenges, USSS is unique in that the semantic categories are often similar in different urban scenes, while the styles can vary significantly due to changes in urban landscapes, weather conditions, lighting, and other factors.
MorphPool: Efficient Non-linear Pooling & Unpooling in CNNs
Pooling is essentially an operation from the field of Mathematical Morphology, with max pooling as a limited special case.
SIGNet: Intrinsic Image Decomposition by a Semantic and Invariant Gradient Driven Network for Indoor Scenes
An ablation study is conducted showing that the use of the proposed priors and progressive CNN increase the IID performance.
Multi-person 3D pose estimation from a single image captured by a fisheye camera
Multi-person 3D pose estimation with absolute depths for a fisheye camera is a challenging task but with valuable applications in daily life, especially for video surveillance.
Invariant Descriptors for Intrinsic Reflectance Optimization
We improve upon their model by introducing illumination invariant image descriptors: color ratios.
PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition
An extensive ablation study and large scale experiments are conducted showing that it is beneficial for edge-driven hybrid IID networks to make use of illumination invariant descriptors and that separating global and local cues helps in improving the performance of the network.
Generative Models for Multi-Illumination Color Constancy
However, most of the existing color constancy methods are designed for single light sources.
EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes
Multimodal large-scale datasets for outdoor scenes are mostly designed for urban driving problems.
Spatio-temporal Features for Generalized Detection of Deepfake Videos
In this paper, we empirically show that existing approaches on image and sequence classifiers generalize poorly to new manipulation techniques.
Novel View Synthesis from Single Images via Point Cloud Transformation
In this paper the argument is made that for true novel view synthesis of objects, where the object can be synthesized from any viewpoint, an explicit 3D shape representation isdesired.
Physics-based Shading Reconstruction for Intrinsic Image Decomposition
We investigate the use of photometric invariance and deep learning to compute intrinsic images (albedo and shading).
Multi-Loss Weighting with Coefficient of Variations
In this paper, we propose a weighting scheme based on the coefficient of variations and set the weights based on properties observed while training the model.
Kinship Identification through Joint Learning Using Kinship Verification Ensembles
The experiments further show significant performance improvement of kinship verification when trained on the same dataset with more realistic distributions.
ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition
The aim is to distinguish strong photometric effects from reflectance variations.
On the Benefit of Adversarial Training for Monocular Depth Estimation
For the quality of the image reconstruction and disparity prediction, a combination of different losses is used, including L1 image reconstruction losses and left-right disparity smoothness.
Deception Detection by 2D-to-3D Face Reconstruction from Videos
Lies and deception are common phenomena in society, both in our private and professional lives.
Improving Face Detection Performance with 3D-Rendered Synthetic Data
In this paper, we provide a synthetic data generator methodology with fully controlled, multifaceted variations based on a new 3D face dataset (3DU-Face).
Color Constancy by GANs: An Experimental Survey
In this paper, we formulate the color constancy task as an image-to-image translation problem using GANs.
Automatic Generation of Dense Non-rigid Optical Flow
There hardly exists any large-scale datasets with dense optical flow of non-rigid motion from real-world imagery as of today.
Inferring Point Clouds from Single Monocular Images by Depth Intermediation
In this paper, we propose a pipeline to generate 3D point cloud of an object from a single-view RGB image.
Joint Learning of Intrinsic Images and Semantic Segmentation
To that end, we propose a supervised end-to-end CNN architecture to jointly learn intrinsic image decomposition and semantic segmentation.
Three for one and one for three: Flow, Segmentation, and Surface Normals
Optical flow, semantic segmentation, and surface normals represent different information modalities, yet together they bring better cues for scene understanding problems.
CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition
On the other hand, recent research use deep learning models as in-and-out black box and do not consider the well-established, traditional image formation process as the basis of their intrinsic learning process.
3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues
Classification and segmentation of 3D point clouds are important tasks in computer vision.
Detect2Rank : Combining Object Detectors Using Learning to Rank
Experiments on the PASCAL VOC07 and VOC10 datasets show that the proposed method significantly outperforms single object detectors, DPM (8. 4%), CN (6. 8%) and EES (17. 0%) on VOC07 and DPM (6. 5%), CN (5. 5%) and EES (16. 2%) on VOC10.
Road Detection by One-Class Color Classification: Dataset and Experiments
These algorithms reduce the effect of lighting variations and weather conditions by exploiting the discriminant/invariant properties of different color representations.
Evaluation of Color STIPs for Human Action Recognition
Existing STIP-based action recognition approaches operate on intensity representations of the image data.
