Search Results for author:
Found 28 papers, 4 papers with code
Context-Sensitive Decision Forests for Object Detection
In this paper we introduce Context-Sensitive Decision Forests - A new perspective to exploit contextual information in the popular decision forest framework for the object detection problem.
GeoF: Geodesic Forests for Learning Coupled Predictors
This paper presents a new and efficient forest based model that achieves spatially consistent semantic image segmentation by encoding variable dependencies directly in the feature space the forests operate on.
Neural Decision Forests for Semantic Image Labelling
In this work we present Neural Decision Forests, a novel approach to jointly tackle data representation- and discriminative learning within randomized decision trees.
Deep Neural Decision Forests
We present Deep Neural Decision Forests - a novel approach that unifies classification trees with the representation learning functionality known from deep convolutional networks, by training them in an end-to-end manner.
Decision Forests, Convolutional Networks and the Models in-Between
We present a systematic analysis of how to fuse conditional computation with representation learning and achieve a continuum of hybrid models with different ratios of accuracy vs. efficiency.
Online Learning With Bayesian Classification Trees
Randomized classification trees are among the most popular machine learning tools and found successful applications in many areas.
Loss Max-Pooling for Semantic Image Segmentation
We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation.
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
The Mapillary Vistas Dataset is a novel, large-scale street-level image dataset containing 25, 000 high-resolution images annotated into 66 object categories with additional, instance-specific labels for 37 classes.
In-Place Activated BatchNorm for Memory-Optimized Training of DNNs
Also, we demonstrate how frequently used checkpointing approaches can be made computationally as efficient as InPlace-ABN.
Ranked #3 on
Semantic Segmentation
on KITTI Semantic Segmentation
Seamless Scene Segmentation
In this work we introduce a novel, CNN-based architecture that can be trained end-to-end to deliver seamless scene segmentation results.
Ranked #2 on
Panoptic Segmentation
on KITTI Panoptic Segmentation
Disentangling Monocular 3D Object Detection
In this paper we propose an approach for monocular 3D object detection from a single RGB image, which leverages a novel disentangling transformation for 2D and 3D detection losses and a novel, self-supervised confidence score for 3D bounding boxes.
3D Object Detection From Monocular Images
Disentanglement
+3
Learning Multi-Object Tracking and Segmentation from Automatic Annotations
Training MOTSNet with our automatically extracted data leads to significantly improved sMOTSA scores on the novel KITTI MOTS dataset (+1. 9%/+7. 5% on cars/pedestrians), and MOTSNet improves by +4. 1% over previously best methods on the MOTSChallenge dataset.
Towards Generalization Across Depth for Monocular 3D Object Detection
While expensive LiDAR and stereo camera rigs have enabled the development of successful 3D object detection methods, monocular RGB-only approaches lag much behind.
Improving Optical Flow on a Pyramid Level
In this work we review the coarse-to-fine spatial feature pyramid concept, which is used in state-of-the-art optical flow estimation networks to make exploration of the pixel flow search space computationally tractable and efficient.
Are we Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?
Pseudo-LiDAR-based methods for monocular 3D object detection have received considerable attention in the community due to the performance gains exhibited on the KITTI3D benchmark, in particular on the commonly reported validation split.
Improving Panoptic Segmentation at All Scales
Crop-based training strategies decouple training resolution from GPU memory consumption, allowing the use of large-capacity panoptic segmentation networks on multi-megapixel images.
Weakly Supervised Multi-Object Tracking and Segmentation
We introduce the problem of weakly supervised Multi-Object Tracking and Segmentation, i. e. joint weakly supervised instance segmentation and multi-object tracking, in which we do not provide any kind of mask annotation.
Dense Prediction with Attentive Feature Aggregation
Our experiments show consistent and significant improvements on challenging semantic segmentation benchmarks, including Cityscapes, BDD100K, and Mapillary Vistas, at negligible computational and parameter overhead.
AutoRF: Learning 3D Object Radiance Fields from Single View Observations
We introduce AutoRF - a new approach for learning neural 3D object representations where each object in the training set is observed by only a single view.
DiffRF: Rendering-Guided 3D Radiance Field Diffusion
We introduce DiffRF, a novel approach for 3D radiance field synthesis based on denoising diffusion probabilistic models.
Panoptic Lifting for 3D Scene Understanding with Neural Fields
We propose Panoptic Lifting, a novel approach for learning panoptic 3D volumetric representations from images of in-the-wild scenes.
OrienterNet: Visual Localization in 2D Public Maps with Neural Matching
We bridge this gap by introducing OrienterNet, the first deep neural network that can localize an image with sub-meter accuracy using the same 2D semantic maps that humans use.
GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields
Neural Radiance Fields (NeRF) have shown impressive novel view synthesis results; nonetheless, even thorough recordings yield imperfections in reconstructions, for instance due to poorly observed areas or minor lighting changes.
VR-NeRF: High-Fidelity Virtualized Walkable Spaces
We present an end-to-end system for the high-fidelity capture, model reconstruction, and real-time rendering of walkable spaces in virtual reality using neural radiance fields.
HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces
Neural radiance fields provide state-of-the-art view synthesis quality but tend to be slow to render.
Robust Gaussian Splatting
In this paper, we address common error sources for 3D Gaussian Splatting (3DGS) including blur, imperfect camera poses, and color inconsistencies, with the goal of improving its robustness for practical applications like reconstructions from handheld phone captures.
Revising Densification in Gaussian Splatting
In this paper, we address the limitations of Adaptive Density Control (ADC) in 3D Gaussian Splatting (3DGS), a scene representation method achieving high-quality, photorealistic results for novel view synthesis.
Mapillary Planet-Scale Depth Dataset
Learning-based methods produce remarkable results on single image depth tasks when trained on well-established benchmarks, however, there is a large gap from these benchmarks to real-world performance that is usually obscured by the common practice of fine-tuning on the target dataset.
